Настройки

Укажите год
-

Небесная энциклопедия

Космические корабли и станции, автоматические КА и методы их проектирования, бортовые комплексы управления, системы и средства жизнеобеспечения, особенности технологии производства ракетно-космических систем

Подробнее
-

Мониторинг СМИ

Мониторинг СМИ и социальных сетей. Сканирование интернета, новостных сайтов, специализированных контентных площадок на базе мессенджеров. Гибкие настройки фильтров и первоначальных источников.

Подробнее

Форма поиска

Поддерживает ввод нескольких поисковых фраз (по одной на строку). При поиске обеспечивает поддержку морфологии русского и английского языка
Ведите корректный номера.
Ведите корректный номера.
Ведите корректный номера.
Ведите корректный номера.
Укажите год
Укажите год
Применить Всего найдено 1048. Отображено 100.
06-01-2022 дата публикации

METADATA GENERATION FOR VIDEO INDEXING

Номер: US20220004574A1
Автор: Figov Zvi, Ofer Irit
Принадлежит:

A video indexing system identifies groups of frames within a video frame sequence captured by a static camera during a same scene. Context metadata is generated for each frame in each group based on an analysis of fewer than all frames in the group. The frames are indexed in a database in association with the generated context metadata. 1. A method comprising:analyzing a sequence of video frame to determine whether the sequence was captured by a static camera; andresponsive to determining that the sequence of frames was captured by the static camera, generating context metadata for each frame in the sequence based on an analysis of fewer than all frames in the sequence.2. The method of claim 1 , further comprising:determining that a select frame of the sequence was captured by a moving camera, andresponsive to the determination, subjecting the select frame to a first series of processing operations for generating the context metadata that is different than a second series of processing operations used to generate the context metadata for the frames in the sequence captured by the static camera.3. The method of claim 2 , wherein the first series of processing operations generates context metadata for the select frame based on an image analysis that is limited to the select frame.4. The method of claim 1 , wherein generating context metadata for each frame in the sequence based on the analysis of fewer than all frames in the sequence further comprises:selecting a keyframe from the sequence;generating at least a portion of the context metadata based on an analysis of the keyframe without analyzing other frames of the sequence; andindexing the other frames of the sequence in association with the generated context metadata.5. The method of claim 4 , wherein generating the context metadata further comprises:generating descriptors for multiple objects present in the keyframe.6. The method of claim 5 , wherein generating the context metadata further comprises:generating a ...

Подробнее
Номер записи: 1
05-01-2017 дата публикации

SYSTEMS AND METHODS FOR GENERATING BOOKMARK VIDEO FINGERPRINTS

Номер: US20170004364A1
Автор: Barr Garrick C., Lahr Nils B.
Принадлежит:

Systems and methods for replacing original media bookmarks of at least a portion of a digital media file with replacement bookmarks is described. A media fingerprint engine detects the location of the original fingerprints associated with the portion of the digital media file and a region analysis algorithm characterizes regions of media file spanning the location of the original bookmarks by data class types. The replacement bookmarks are associated with the data class types and are overwritten or otherwise are substituted for the original bookmarks. The replacement bookmarks then are subjected to a fingerprint matching algorithm that incorporates media timeline and media related metadata. 1. A method for generating video fingerprints comprising:sharing timeline and metadata of an original digital media file including at least one of a video digital file and an audio digital file;identifying a region within the original media file;bookmarking the identified region with a fingerprinting algorithm;detecting a bookmarked region of a duplicate of the original media file using the fingerprinting algorithm; andcomparing the bookmarked region of the original media file to the bookmarked region of the duplicate.2. The method of claim 1 , wherein identifying a region of the original digital media file includes determining data types within the digital media file.3. The method of claim 2 , wherein determining data types includes at least one of a pixel luminescence value claim 2 , a region of pixel luminescence values claim 2 , an indicator of object motion claim 2 , a change in sound volume claim 2 , and a change in sound types.4. The method of claim 1 , wherein detecting a bookmarked region includes selecting a frame group claim 1 , examining for the presence of matchable characteristics in the frame group claim 1 , applying a region algorithm to the frame group claim 1 , removing repetitive occurrences of the matchable characteristics claim 1 , and defining a path of the ...

Подробнее
Номер записи: 2
02-01-2020 дата публикации

Method and Apparatus for Multi-Dimensional Content Search and Video Identification

Номер: US20200004779A1
Автор: Merchant Shashank, Piereira Jose Pio, Stojancic Mihailo M.
Принадлежит:

A multi-dimensional database and indexes and operations on the multi-dimensional database are described which include video search applications or other similar sequence or structure searches. Traversal indexes utilize highly discriminative information about images and video sequences or about object shapes. Global and local signatures around keypoints are used for compact and robust retrieval and discriminative information content of images or video sequences of interest. For other objects or structures relevant signature of pattern or structure are used for traversal indexes. Traversal indexes are stored in leaf nodes along with distance measures and occurrence of similar images in the database. During a sequence query, correlation scores are calculated for single frame, for frame sequence, and video clips, or for other objects or structures. 1. A computer-implemented method for storing information associated with videos in a reference database using hash values as traversal indexes , the computer-implemented method comprising: obtaining, by a processor, data associated with the video sequence,', 'determining, by the processor, a multi-dimensional vector signature of a region of a frame of the video sequence,', 'determining, by the processor, a hash value based on the multi-dimensional vector signature, and', 'storing the data associated with the video sequence at a leaf node of a plurality of leaf nodes, wherein the leaf node is addressable by the hash value., 'for each of multiple video sequences2. The computer-implemented method of claim 1 , wherein the region comprises multiple sectors claim 1 , and wherein the multi-dimensional vector signature represents each sector.3. The computer-implemented method of claim 2 , wherein determining the multi-dimensional vector signature comprises comparing features within each sector to a threshold value to generate a value for the sector.4. The computer-implemented method of claim 2 , wherein the region is a rectangular ...

Подробнее
Номер записи: 3
02-01-2020 дата публикации

Method and Apparatus for Multi-Dimensional Content Search and Video Identification

Номер: US20200004780A1
Автор: Merchant Shashank, Pereira Jose Pio, Stojancic Mihailo M.
Принадлежит:

A multi-dimensional database and indexes and operations on the multi-dimensional database are described which include video search applications or other similar sequence or structure searches. Traversal indexes utilize highly discriminative information about images and video sequences or about object shapes. Global and local signatures around keypoints are used for compact and robust retrieval and discriminative information content of images or video sequences of interest. For other objects or structures relevant signature of pattern or structure are used for traversal indexes. Traversal indexes are stored in leaf nodes along with distance measures and occurrence of similar images in the database. During a sequence query, correlation scores are calculated for single frame, for frame sequence, and video clips, or for other objects or structures. 1. A computer-implemented method for storing information associated with a video sequence in a reference database , the computer-implemented method comprising:obtaining, by a processor, data associated with the video sequence; and determining, by the processor, respective global features of a global region of interest,', 'determining, by the processor, respective local features of a respective keypoint within the global region of interest, wherein, for multiple frames of the set of frames of the video sequence, the respective keypoints correspond to different respective locations within the global region of interest,', 'generating, by the processor, a respective signature using both the global features for the frame and the local features for the frame,', 'determining, by the processor, a respective hash value for the frame based on the signature for the frame, and', 'storing, by the processor, the data associated with the video sequence in the reference database in association with the hash value for the frame., 'for each frame of a set of frames of the video sequence2. The computer-implemented method of claim 1 , wherein ...

Подробнее
Номер записи: 4
02-01-2020 дата публикации

Method and Apparatus for Multi-Dimensional Content Search and Video Identification

Номер: US20200004781A1
Автор: Merchant Shashank, Pereira Jose Pio, Stojancic Mihailo M.
Принадлежит:

A multi-dimensional database and indexes and operations on the multi-dimensional database are described which include video search applications or other similar sequence or structure searches. Traversal indexes utilize highly discriminative information about images and video sequences or about object shapes. Global and local signatures around keypoints are used for compact and robust retrieval and discriminative information content of images or video sequences of interest. For other objects or structures relevant signature of pattern or structure are used for traversal indexes. Traversal indexes are stored in leaf nodes along with distance measures and occurrence of similar images in the database. During a sequence query, correlation scores are calculated for single frame, for frame sequence, and video clips, or for other objects or structures. 1. A computer-implemented method comprising:obtaining, by a processor, a first query index and a second query index that are derived from different respective features of a frame of a query video;determining, by the processor, that a distance measure between the first query index and a candidate database index of a reference database satisfies a threshold condition, wherein the candidate database index corresponds to a frame of an original video;determining, by the processor, a correlation score for the frame of the query video and the frame of the original video based on a comparison of the second query index and an additional candidate database index corresponding to the frame of the original video;based at least on the correlation score, determining, by the processor, a video sequence likelihood indicative of a confidence of match between the query video and the original video; andbased on the video sequence likelihood, providing, by the processor, a results list that includes a name of the original video.2. The computer-implemented method of claim 1 , wherein the second query index corresponds to a texture signature of a ...

Подробнее
Номер записи: 5
02-01-2020 дата публикации

Method and Apparatus for Multi-Dimensional Content Search and Video Identification

Номер: US20200004782A1
Автор: Jose Pio Pereira, Mihailo M. Stojancic, Shashank Merchant
Принадлежит: Gracenote Inc

A multi-dimensional database and indexes and operations on the multi-dimensional database are described which include video search applications or other similar sequence or structure searches. Traversal indexes utilize highly discriminative information about images and video sequences or about object shapes. Global and local signatures around keypoints are used for compact and robust retrieval and discriminative information content of images or video sequences of interest. For other objects or structures relevant signature of pattern or structure are used for traversal indexes. Traversal indexes are stored in leaf nodes along with distance measures and occurrence of similar images in the database. During a sequence query, correlation scores are calculated for single frame, for frame sequence, and video clips, or for other objects or structures.

Подробнее
Номер записи: 6
13-01-2022 дата публикации

DEVICE AND METHOD FOR GENERATING SUMMARY VIDEO

Номер: US20220012500A1
Автор: HAN Junkyu, LEE Pius, TAK Hyunuk
Принадлежит:

A method for generating a summary video includes generating a user emotion graph of a user watching a first video. The method also includes obtaining a character emotion graph for a second video, by analyzing an emotion of a character in a second video that is a target of summarization. The method further includes obtaining an object emotion graph for an object in the second video, based on an object appearing in the second video. Additionally the method includes obtaining an image emotion graph for the second video, based on the character emotion graph and the object emotion graph. The method also includes selecting at least one first scene in the second video by comparing the user emotion graph with the image emotion graph. The method further includes generating the summary video of the second video, based on the at least one first scene. 1. A method , performed by a device , of generating a summary video , the method comprising:obtaining a user image in which a user watching a first video is photographed, during playback of the first video;generating a user emotion graph of the user watching the first video, by analyzing an emotion of the user in the obtained user image;obtaining a character emotion graph for a second video, by analyzing an emotion of a character in the second video that is a target of summarization;obtaining an object emotion graph for an object in the second video, based on the object appearing in the second video;obtaining an image emotion graph for the second video, based on the character emotion graph and the object emotion graph;selecting at least one first scene in the second video by comparing the user emotion graph of the user that watched the first video with the image emotion graph for the second video; andgenerating the summary video of the second video, based on the at least one first scene.2. The method of claim 1 , further comprising:selecting at least one second scene in the second video, based on emotion scores in the image ...

Подробнее
Номер записи: 7
07-01-2021 дата публикации

COMPUTER-IMPLEMENTED METHOD

Номер: US20210004601A1
Автор: Lancia Samuel
Принадлежит:

A computer-implemented method of identifying an object within a video stream from a camera, and determining the consistency with which the object is identified within plural temporally spaced video frames of the video stream. 1. A computer-implemented method of identifying an object within a video stream collected by a camera , and determining the consistency with which the object is identified within plural temporally spaced video frames of the video stream , the method comprising:receiving a first video frame of the plural video frames at a first time;identifying an object within the first video frame;labelling the object with a label;storing the label of the object in association with an identifier of a first position of the object within the first video frame;receiving a second video frame of the plural video frames corresponding to a second time, temporally different from the first time;identifying an object within the second video frame;labelling the object, wherein the object in the second video frame is the same as the object in the first video frame;deriving a motion vector between the first video frame and the second video frame, using the position of the object in the first frame and the position of the object in the second frame; anddetermining a consistency with which the object in the first video frame and the object in the second video frame have been identified, using the derived cumulative motion vector.2. The computer-implemented method of claim 1 , wherein identifying the object within the first and/or second video frame is performed via an object classifier algorithm.3. The computer-implemented method of claim 1 , wherein the camera is a first camera claim 1 , and the method further comprises the steps of:receiving a comparator video frame from a second video stream of a second camera, said second video stream having a field of view at least partially overlapping with a field of view of the video stream of the first camera, the comparator video ...

Подробнее
Номер записи: 8
04-01-2018 дата публикации

Systems and Methods for Intelligent Media Content Segmentation and Analysis

Номер: US20180005041A1
Автор: Accardo Anthony M., Ettinger Katharine S., FARRÉ GUIU Miquel Angel, Lindquist Alexis, Luu Jack, Narayan Nimesh, Pao Alan, Petrillo Matthew, Volodarsky Bareket Lena
Принадлежит:

There is provided a system including a non-transitory memory storing an executable code and a hardware processor executing the executable code to receive a media content including a plurality of frames, divide the media content into a plurality of shots, each of the plurality of shots including a plurality of frames of the media content based on a first similarity between the plurality of frames, determine a plurality of sequential shots of the plurality of shots to be part of a first sub-scene of a plurality of sub-scenes of a scene based on a timeline continuity of the plurality of sequential shots, identify each of the plurality of shots of the media content and each of the plurality of sub-scenes with a corresponding beginning time code and a corresponding ending time code. 1. A system comprising:a non-transitory memory storing an executable code; receive a media content including a plurality of frames;', 'divide the media content into a plurality of shots, each of the plurality of shots including a plurality of frames of the media content based on a first similarity between the plurality of frames;', 'determine a plurality of sequential shots of the plurality of shots to be part of a first sub-scene of a plurality of sub-scenes of a scene based on a timeline continuity of the plurality of sequential shots;', 'identify each of the plurality of shots of the media content and each of the plurality of sub-scenes with a corresponding beginning time code and a corresponding ending time code., 'a hardware processor executing the executable code to2. The system of claim 1 , wherein the hardware processor further executes the executable code to:determine one or more sequential sub-scenes of the plurality of sub-scenes to be part of the scene; andidentify the scene with a corresponding beginning time code and a corresponding ending time code.3. The system of claim 1 , wherein the hardware processor further executes the executable code to:receive a user input annotating ...

Подробнее
Номер записи: 9
02-01-2020 дата публикации

STANDALONE VIDEO CLASSIFICATION

Номер: US20200005047A1
Автор: Bills Bonnie, Hedayati Fares, Joshi Mahesh S., Polatkan Gungor
Принадлежит:

Techniques for classifying videos as standalone or non-standalone are provided. Feature (or attribute) values associated with a particular video are identified. Feature values are extracted from metadata associated with the particular video and/or from within a transcript of the particular video. The extracted feature values of the particular video are input to a rule-based or a machine-learned model and the model scores the particular video. Once a determination pertaining to whether the particular video is standalone is made, information about the particular video being a standalone video is presented to one or more users within the network. 1. A method comprising:identifying multiple co-viewing feature values between a particular video item and a plurality of other video items;determining a time duration of the particular video item;based on the multiple co-viewing feature values and the time duration, making a determination whether the particular video is a standalone video;based on the determination, causing information about the particular video item being a standalone video to be presented to one or more users;wherein the method is performed by one or more computing devices.2. The method of claim 1 , further comprising:storing training data that comprises a plurality of training instances, wherein each training instance in the plurality of training instances corresponds to a different video item, includes a plurality of feature values pertaining to the different video item, and includes a label that indicates whether the different video item is a standalone video;using one or more machine learning techniques to train a classification model based on the training data;wherein making the determination comprises inserting the multiple co-viewing feature values into the classification model that generates an output that is used to determine whether the particular video item is a standalone video.3. The method of claim 1 , further comprising:identifying text ...

Подробнее
Номер записи: 10
02-01-2020 дата публикации

TRANSFORMATION OF VIDEO STREAMS

Номер: US20200005048A1
Автор: Bharde Madhumita, BHATTACHARYA Suparna, Shree Dileep Deepa
Принадлежит:

Example aspects for transformation of video streams include searching for a first signature of a segment of a video stream in an index comprising a first level signature of each of a plurality of stored segments. In response to identifying a first set of similar segments from the stored segments, a second signature of the segment may be determined. In response to identifying a second set of similar segments from the first set of similar segments based on the second signature, a matching segment may be ascertained from the second set of similar segments. The matching segment may be provided for being stored in place of the segment in a storage medium. 1. A method for transformation of a video stream at an edge device , the method comprising , for each segment of the video stream:searching for a first signature of a segment of the video stream in an index comprising a first level signature of each of a plurality of stored segments;in response to identifying a first set of similar segments from the stored segments, determining a second signature of the segment;in response to identifying a second set of similar segments from the first set of similar segments based on the second signature, ascertaining a matching segment from the second set of similar segments; andproviding the matching segment for being stored in place of the segment in a storage medium.2. The method of claim 1 , whereinthe first signature is based on summarized descriptors of a scene in the segment and the first set of similar segments includes similar segments that are approximate matches for the segment; andthe second signature is based on detailed descriptors of the scene in the segment and the second set of similar segments includes the similar segments that are near exact matches for the segment.3. The method of claim 1 , wherein a similar segment of the first set of similar segments is selected to be in the second set of similar segments when a difference value obtained on comparison between the ...

Подробнее
Номер записи: 11
03-01-2019 дата публикации

SCENE AND ACTIVITY IDENTIFICATION IN VIDEO SUMMARY GENERATION

Номер: US20190005333A1
Автор: Newman David A., Silver Adam
Принадлежит:

Video and corresponding metadata is accessed. Events of interest within the video are identified based on the corresponding metadata, and best scenes are identified based on the identified events of interest. A video summary can be generated including one or more of the identified best scenes. The video summary can be generated using a video summary template with slots corresponding to video clips selected from among sets of candidate video clips. Best scenes can also be identified by receiving an indication of an event of interest within video from a user during the capture of the video. Metadata patterns representing activities identified within video clips can be identified within other videos, which can subsequently be associated with the identified activities. 1. A method for identifying video scenes , the method comprising:accessing a video of an activity, the activity including an event at a moment within the video;obtaining an identification of a type of the activity;obtaining an identification of a type of the event; the length is a first length based on the type of the activity being of a first activity type and the type of the event being of a first event type;', 'the length is a second length based on the type of the activity being of the first activity type and the type of the event being of a second event type;', 'the length is a third length based on the type of the activity being of a second activity type and the type of the event being of the first event type; and', 'the length is a fourth length based on the type of the activity being of the second activity type and the type of the event being of the second event type,', the first length is different from the second length, the third length, and the fourth length;', 'the second length is different from the third length and the fourth length; and', 'the third length is different from the fourth length; and, 'wherein], 'identifying a scene of the video for the event, the scene including a length of ...

Подробнее
Номер записи: 12
03-01-2019 дата публикации

METHODS, SYSTEMS, AND MEDIA FOR GENERATING A SUMMARIZED VIDEO WITH VIDEO THUMBNAILS

Номер: US20190005334A1
Автор: Grundmann Matthias, Hawkins Alexandra Ivanna, Ioffe Sergey
Принадлежит:

Methods, systems, and media for summarizing a video with video thumbnails are provided. In some embodiments, the method comprises: receiving a plurality of video frames corresponding to the video and associated information associated with each of the plurality of video frames; extracting, for each of the plurality of video frames, a plurality of features; generating candidate clips that each includes at least a portion of the received video frames based on the extracted plurality of features and the associated information; calculating, for each candidate clip, a clip score based on the extracted plurality of features from the video frames associated with the candidate clip; calculating, between adjacent candidate clips, a transition score based at least in part on a comparison of video frame features between frames from the adjacent candidate clips; selecting a subset of the candidate clips based at least in part on the clip score and the transition score associated with each of the candidate clips; and automatically generating an animated video thumbnail corresponding to the video that includes a plurality of video frames selected from each of the subset of candidate clips. 1. A method for summarizing videos , the method comprising:receiving, using a hardware processor, a video content item comprising a plurality of video frames;extracting, for each of the plurality of video frames of the video content item, a plurality of features;generating a plurality of candidate clips that each include a portion of the plurality of frames based on the extracted plurality of features indicating that the portion of the plurality of frames includes interesting content;selecting a first candidate clip and a second candidate clip that are adjacent candidate clips based on a transition score that includes a penalty for containing similar looking frames; andautomatically generating an animated video thumbnail corresponding to the video that includes the first candidate clip and the ...

Подробнее
Номер записи: 13
07-01-2021 дата публикации

System and Method for Detecting and Classifying Direct Response Advertisements Using Fingerprints

Номер: US20210006859A1
Автор: Cho Hoon-Young, Kim Kil-youn, Lee Jaehyung, Lonjon David, SONG Ji-Hoon
Принадлежит:

System and method for detecting and classifying direct response advertisements. The system includes a unit for generating an advertisement candidate segment for an advertisement section detected from a broadcast stream; a matching unit for determining whether the candidate segment matches each advertisement segment stored in a database (DB); a unit for, if the matching unit determines that a segment matching the candidate segment is not present, determining whether the candidate segment is a direct response advertisement; a registration unit for storing the candidate segment, determined to be a direct response advertisement, as an advertisement segment that is the direct response advertisement in the DB; and a direct response advertisement grouping unit for, if the matching unit determines that an advertisement segment matching the candidate segment is present, and the matching segment is a direct response advertisement, grouping the candidate segment with DB-stored advertisement segments that are direct response advertisements. 1. A method comprising:receiving one or more broadcast streams comprising a first advertisement segment and a second advertisement segment;making a first determination that the first advertisement segment non-identically matches a third advertisement segment within a threshold extent of similarity, wherein the third advertisement segment is a master segment;storing data indicating that the first advertisement segment is a first variation segment of the third advertisement segment;making a second determination that the second advertisement segment non-identically matches the third advertisement segment within the threshold extent of similarity and making a third determination that the second advertisement segment does not identically match the first advertisement segment; andstoring data indicating that the second advertisement segment is a second variation segment of the third advertisement segment.2. The method of claim 1 , wherein the one ...

Подробнее
Номер записи: 14
20-01-2022 дата публикации

METHODS AND SYSTEMS FOR USING MULTIPLE DATA STRUCTURES TO PROCESS SURGICAL DATA

Номер: US20220020486A1
Автор: Chow Andre, Giataganas Petros, Luengo Muntion Imanol, Nehme Jean, Stoyanov Danail
Принадлежит:

The present disclosure relates to processing data streams from a surgical procedure using multiple interconnected data structures to generate and/or continuously update an electronic output. Each surgical data structure is used to determine a current node associated with a characteristic of a surgical procedure and present relevant metadata associated with the surgical procedure. Each surgical data structure includes at least one node interconnected to one or more nodes of another data structure. The interconnected nodes between one or more data structures includes relational metadata associated with the surgical procedure. 120-. (canceled)21. A computer-implemented method comprising:accessing, by a processor, a surgical dataset associated with a surgical procedure, the surgical dataset comprising a surgical video of the surgical procedure being performed; a first data structure that comprises a first plurality of nodes and a first plurality of edges, wherein a first node from the first data structure represents a procedural state in the surgical procedure;', 'a second data structure that comprises a second plurality of nodes and a second plurality of edges, wherein a second node from the second data structure represents a surgical tool used in the surgical procedure;', 'adding, by the processor, an interconnecting edge between the first node and the second node based on a surgical event detected in the surgical video, wherein the interconnecting edge is associated with a relational metadata representing a use of the surgical tool of the second node in the procedural state of the first node;', 'generating, by the processor, electronic data to be associated with a portion of the surgical video, the electronic data describing an operational note based at least on the procedural state of the first node, a data associated with the second node, and the relational metadata associated with the interconnecting edge between the first node and the second node, the portion ...

Подробнее
Номер записи: 15
27-01-2022 дата публикации

Video processing for embedded information card localization and content extraction

Номер: US20220027631A1
Автор: Dennis KANYGIN, Mihailo Stojancic, Warren Packard
Принадлежит: STATS LLC

Metadata for one or more highlights of a video stream may be extracted from one or more card images embedded in the video stream. The highlights may be segments of the video stream, such as a broadcast of a sporting event, that are of particular interest. According to one method, video frames of the video stream are stored. One or more information cards embedded in a decoded video frame may be detected by analyzing one or more predetermined video frame regions. Image segmentation, edge detection, and/or closed contour identification may then be performed on identified video frame region(s). Further processing may include obtaining a minimum rectangular perimeter area enclosing all remaining segments, which may then be further processed to determine precise boundaries of information card(s). The card image(s) may be analyzed to obtain metadata, which may be stored in association with at least one of the video frames.

Подробнее
Номер записи: 16
14-01-2016 дата публикации

IMAGE PROCESSOR, METHOD AND PROGRAM

Номер: US20160012295A1
Автор: IMOTO Kazunori, Mihara Isao, Takahashi Shihomi
Принадлежит:

According to one embodiment, an image processor includes a writing amount detector and an end timing detector. The writing amount detector detects a writing amount in an image. The end timing detector detects an end timing of writing based on the writing amount detected by the writing amount detector. 1. An image processor comprising:a writing amount detector configured to detect a writing amount in an image; andan end timing detector configured to detect an end timing of writing based on the writing amount detected by the writing amount detector.2. The image processor of claim 1 , further comprising:a reproduction module configured to reproduce the image in accordance with chapters obtained by dividing the image at the end timing.3. The image processor of claim 1 , further comprising:a display configured to display chapter images indicative of chapters obtained by dividing the image at the end timing; anda reproduction module configured to reproduce, in response to selection of any one of the chapter images displayed by the display, the image from an end timing corresponding to the selected chapter image or an end timing corresponding to a preceding chapter image.4. The image processor of claim 3 , whereinthe display is configured to display an image corresponding to the end timing as the chapter image.5. The image processor of claim 3 , whereinthe display is configured to extract images of portions in which writing is temporarily stopped from images corresponding to end timings, combine the extracted images into a single chapter image and display the single chapter image.6. The image processor of claim 3 , whereinthe display is configured to display the chapter image while highlighting an image of portion in which writing is temporarily stopped.7. The image processor of claim 1 , whereinthe writing amount detector is configured to extract a background and writing blocks from the image and detect a ratio of the writing blocks to the background as the writing amount ...

Подробнее
Номер записи: 17
14-01-2016 дата публикации

System and Method For Processing A Video Stream To Extract Highlights

Номер: US20160012296A1
Автор: Xing Eric, Zhou Bin
Принадлежит: CARNEGIE MELLON UNIVERSITY

With the widespread availability of video cameras, we are facing an ever-growing enormous collection of unedited and unstructured video data. Due to lack of an automatic way to generate highlights from this large collection of video streams, these videos can be tedious and time consuming to index or search. The present invention is a novel method of online video highlighting, a principled way of generating a short video highlight summarizing the most important and interesting contents of a potentially very long video, which is costly both time-wise and financially for manual processing. Specifically, the method learns a dictionary from given video using group sparse coding, and updates atoms in the dictionary on-the-fly. A highlight of the given video is then generated by combining segments that cannot be sparsely reconstructed using the learned dictionary. The online fashion of the method enables it to process arbitrarily long videos and starts generating highlights before seeing the end of the video, both attractive characteristics for practical applications. 1. A system for extracting video highlights from a video stream comprising:a. storage, containing said video stream in digital form; and i. breaking said video stream into segments containing a preset number of frames;', 'ii. reading an initial plurality of segments and constructing a dictionary based on said plurality of segments, said dictionary containing data summarizing the content of said initial plurality of segments;', 'iii. reading the next segment from said video stream;', 'iv. determining if the content of said next segment is represented in said dictionary and, if so, excluding said next segment from said video highlights; otherwise, adding said next segment to said video highlights;', 'v. updating said dictionary when segments are added to said video highlights to reflect a summary of the content of said added segment; and', 'vi. repeating steps iii.-iv. until all segments in said video stream ...

Подробнее
Номер записи: 18
09-01-2020 дата публикации

Video summarization using semantic information

Номер: US20200012864A1
Автор: Krishna Kumar Singh, MYUNG HWANGBO, Omesh Tickoo, Teahyung Lee
Принадлежит: Intel Corp

An apparatus for video summarization using sematic information is described herein. The apparatus includes a controller, a scoring mechanism, and a summarizer. The controller is to segment an incoming video stream into a plurality of activity segments, wherein each frame is associated with an activity. The scoring mechanism is to calculate a score for each frame of each activity, wherein the score is based on a plurality of objects in each frame. The summarizer is to summarize the activity segments based on the score for each frame.

Подробнее
Номер записи: 19
09-01-2020 дата публикации

ADAPTING TO APPEARANCE VARIATIONS WHEN TRACKING A TARGET OBJECT IN VIDEO SEQUENCE

Номер: US20200012865A1
Автор: GAVVES Efstratios, SMEULDERS Arnold Wilhelmus Maria, TAO Ran
Принадлежит:

A method of tracking a position of a target object in a video sequence includes identifying the target object in a reference frame. A generic mapping is applied to the target object being tracked. The generic mapping is generated by learning possible appearance variations of a generic object. The method also includes tracking the position of the target object in subsequent frames of the video sequence by determining whether an output of the generic mapping of the target object matches an output of the generic mapping of a candidate object. 1. A device for tracking a target object in a sequence of images captured by a vehicle-mounted camera , comprising:a memory; and obtain a generic mapping of an object, wherein the generic mapping is based on appearance variations of the object;', 'obtain an image of the target object from the sequence of images captured by the vehicle-mounted camera; and', 'identify the target object in a subsequent image by determining that the features of the generic mapping of the object match features of the target object in the subsequent image., 'a processor, coupled to the memory, configured to2. The device of claim 1 , wherein the processor is further configured to:obtain an image of the object in a sequence of reference frames; andgenerate the generic mapping of the object by learning appearance variations of the object.3. The device of claim 2 , wherein learning appearance variations of the object comprises offline learning based on videos or images in a repository.4. The device of claim 1 , wherein the object corresponds to one or more of a vehicle wheel claim 1 , a vehicle windshield claim 1 , a traffic light claim 1 , or a traffic sign.5. The device of claim 1 , wherein determining whether features of the generic mapping of the object match features of the target object in the subsequent image comprises determining whether features of the generic mapping of the object match features of a candidate box of a plurality of candidate boxes ...

Подробнее
Номер записи: 20
12-01-2017 дата публикации

MEDIA FINGERPRINTING FOR CONTENT DETERMINATION AND RETRIEVAL

Номер: US20170013314A1
Автор: Mallinson Dominic S.
Принадлежит:

Audio fingerprinting and other media matching technologies can be used to identify broadcast media, such as television shows and radio broadcasts. A user device can record image, audio, and/or video information and upload information to a matching service that is able to use matching technology to identify the media and provide supplemental content or information to the user. The user might receive information identifying a product in an advertisement, identifying an actor on screen in a movie at a particular time, or other such information. In some embodiments, the user can receive access to a digital copy of the captured media, such as the ability to download a copy of a program in which a user expressed interest. Since a user might capture media information after the point of interest, a device can buffer a window of recently captured media in order to attempt to identify the intended media. 1. A method for requesting information , comprising:receiving media content streamed to a user device;playing said media content on said user device;capturing a portion of said media content, wherein said media content comprises first content and second content, wherein said first content is of interest to a user of said user device, and wherein said portion of said media content directly corresponds to said second content and not to said first content;assigning a time stamp to said captured portion corresponding to when said portion was captured;hashing said captured portion of said media content to obtain a hashed value;delivering said hashed value and said time stamp to a back-end server for identification of said media content in an initial request for supplemental information associated with said first content of interest to said user, wherein said back-end server is configured to identify said second content using said hashed value and correlate said second content with said first content using said time stamp;receiving for display from said back-end server a first ...

Подробнее
Номер записи: 21
10-01-2019 дата публикации

IDENTIFYING INTERESTING PORTIONS OF VIDEOS

Номер: US20190013047A1
Автор: Bharat Krishna, Frueh Christian, Grundmann Matthias, Hickman Ryan Michael, Pantofaru Caroline Rebecca, Wait Arthur, YAGNIK JAY
Принадлежит:

A plurality of videos is analyzed (in real time or after the videos are generated) to identify interesting portions of the videos. The interesting portions are identified based on one or more of the people depicted in the videos, the objects depicted in the videos, the motion of objects and/or people in the videos, and the locations where people depicted in the videos are looking. The interesting portions are combined to generate a content item. 1. A method comprising:receiving a plurality of videos of an event, wherein each video originates from a camera in a plurality of cameras, wherein operation of the plurality of cameras are synchronized with each other, and wherein each video is associated with a viewpoint of the event; (i) a motion of one or more objects in corresponding portions of the first video and a motion of one or more objects in corresponding portions of the second video respectively,', '(ii) a number of objects depicted in the corresponding portions of the first video and the corresponding portions of the second video respectively, wherein a larger number of objects in a portion of the first video or the second video results in a higher saliency score for the portion of the first video or the second video; and', a type of event,', 'rules associated with the type of event,', 'a schedule associated with the event,', 'a presence of one or more objects associated with the type of event in the corresponding portions of the first video and the corresponding portions of the second video respectively,', 'a location where one or more people in an audience are looking, in the corresponding portions of the first video and the corresponding portions of the second video respectively; and, '(iii) at least one of], 'determining first saliency scores for portions of a first video of the plurality of videos and second saliency scores for portions of a second video of the plurality of videos, wherein the first saliency scores and second saliency scores are based ...

Подробнее
Номер записи: 22
14-01-2021 дата публикации

VIDEO CURATION SERVICE FOR PERSONAL STREAMING

Номер: US20210012808A1
Автор: Pratt James, Zavesky Eric
Принадлежит: AT&T Intellectual Property I, L.P.

Aspects of the subject disclosure may include, for example, a device that includes a processing system with a processor, and a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations such as receiving user input comprising a keyword identifying an object, monitoring a video recording during a generation of the video recording by a camera, wherein the monitoring includes detecting the object being captured by the camera, creating a video clip from the video recording, wherein the video clip comprises a start point and a stop point in the video recording determined by a machine learning algorithm, and sending a notification of the creating of the video clip. Other embodiments are disclosed. 1. A method , comprising:receiving, by a processing system including a processor, user input comprising one or more keywords indicating a context of an event;monitoring, by the processing system, generation of a video recording to determine that a portion of the video recording corresponds to the context indicated by the one or more keywords;receiving, by the processing system, messages via a network from equipment of a plurality of persons associated with the user, the messages corresponding to the context indicated by the one or more keywords;defining, by the processing system, end points of a video clip in the video recording using a machine learning algorithm;sending, by the processing system, a notification that the event has been detected in the video recording;refraining from creating video clips from the video recording in accordance with information comprised in the user input;receiving, by the processing system, user feedback associated with the video clip; andupdating, by the processing system, the machine learning algorithm based on the user feedback.2. The method of claim 1 , wherein the information comprised in the user input indicates a circumstance under which to apply a privacy blackout.3. The ...

Подробнее
Номер записи: 23
14-01-2021 дата публикации

Dynamic audiovisual segment padding for machine learning

Номер: US20210012809A1
Автор: Aaron K. Baughman, Gray CANNON, Stephen C. Hammer
Принадлежит: International Business Machines Corp

Techniques for padding audiovisual clips (for example, audiovisual clips of sporting events) for the purpose of causing the clip to have a predetermined duration so that the padded clip can be evaluated for viewer interest by a machine learning (ML) algorithm. The unpadded clip is padded with audiovisual segment(s) that will cause the padded clip to have a level of viewer interest that it would have if the unpadded clip had been longer. In some embodiments the padded segments are synthetic images generated by a generative adversarial network such that the synthetic images would have the same level of viewer interest (as adjudged by an ML algorithm) as if the unpadded clip had been shot to be longer.

Подробнее
Номер записи: 24
14-01-2016 дата публикации

AUTOMATIC TIME SIGNATURE-BASED VIDEO MATCHING FOR A CAMERA NETWORK

Номер: US20160014305A1
Автор: DIENER Stefan, SCHLATTMANN Markus
Принадлежит:

A method for automatically matching video streams from two cameras of a camera network includes obtaining a video stream of frames that are acquired by each of the cameras. Each video stream includes images of moving objects. A time signature for each of the video streams is calculated. Each time signature is indicative of a time at which an image of one the objects is located at a predetermined part of the frame. A temporal offset of one of the signatures relative to the other signature is calculated such that, when applied to one of the signatures, a correspondence between the signatures is maximized. The temporal offset is applicable to video streams that are acquired by the two cameras to determine if a moving object that is imaged by one of the cameras is identical to a moving object that is imaged by the other camera. 1. A method for automatically matching video streams from two cameras of a camera network , the method comprising:obtaining a video stream of frames that are acquired by each of the cameras, each video stream including images of a plurality of moving objects;calculating a time signature for each of the video streams, each time signature being indicative of a time at which an image of one of said plurality of moving objects is located at a predetermined part of the frame; andcalculating a temporal offset of one of the signatures relative to the other signature that, when applied to said one of the signatures, substantially maximizes a correspondence between said one of the signatures and the other signature, the temporal offset being applicable to video streams that are acquired by the two cameras to determine if a moving object that is imaged by one of the cameras is identical to a moving object that is imaged by the other of the cameras.2. The method of claim 1 , wherein said plurality of moving objects moves along a substantially common path.3. The method of claim 2 , wherein the predetermined part is located on an image of the path.4. The ...

Подробнее
Номер записи: 25
14-01-2016 дата публикации

Systems and Methods for Generating Video Summary Sequences From One or More Video Segments

Номер: US20160014482A1
Автор: Chen David Mo, Chen Huizhong, Daneshi Maryam, de Araujo Andre Filgueiras, Girod Bernd, Tsai Shanghsuan, Vajda Peter, Yu Matthew Chuck-Jun
Принадлежит:

Next-generation media consumption is likely to be more personalized, device agnostic, and pooled from many different sources. Systems and methods in accordance with embodiments of the invention can provide users with personalized video content feeds providing the video content that matters most to them. In several embodiments, a multi-modal segmentation process is utilized that relies upon cues derived from video, audio and/or text data present in a video data stream. In a number of embodiments, video streams from a variety of sources are segmented. Links are identified between video segments and between video segments and online articles containing additional information relevant to the video segments. In many embodiments, video clips from video segments can be ordered and concatenated based on importance in order to generate news briefs. 1. A method of generating video summary sequences , the method comprising:obtaining a set of annotated video segments using a video summarization system;extracting a set of video clips from the set of annotated video segments based upon clipping cues using the video summarization system, where a video clip in the set of video clips comprises at least one key feature and metadata describing the length of the video clip;generating scoring data using a video summarization system, wherein the scoring data comprises at least one scoring metric for each video clip in the set of video clips, where the at least one scoring metric describes the at least one key feature of each video clip utilized to determine the relative importance of each video clip within the set of video clips;selecting a subset of the set of video clips based on the generated scoring data such that the sum of the lengths of the video clips in the selected subset of video clips is within a predefined range of lengths using the video summarization system;determining a sequence of at least a subset of video clips from the selected subset of video clips using the video ...

Подробнее
Номер записи: 26
03-02-2022 дата публикации

APPARATUS AND METHOD FOR DETECTING SUSPICIOUS CONTENT

Номер: US20220036088A1
Автор: Beattie, Griesmer Stephen J., JR. James Gordon
Принадлежит: AT&T Intellectual Property I, L.P.

Aspects of the subject disclosure may include, for example, receiving data associated with a video, applying the data to a machine learning model to obtain a prediction regarding an accuracy of an assertion included in the video, responsive to the prediction indicating that the assertion is accurate, transmitting the video to a processing system including a processor, and responsive to the prediction indicating that the assertion in inaccurate, preventing a transmission of the video to the processing system. Other embodiments are disclosed. 1. A device , comprising:a processing system including a processor; anda memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations, the operations comprising:processing a digest to generate a cascade assembly, the digest comprising first video content data associated with a first video;processing the cascade assembly to generate a veracity indication that represents an accuracy of at least one subject matter included in the first video;generating a model in accordance with at least the veracity indication; andapplying second video content data to the model to generate a prediction regarding a likelihood of whether a subject matter of a second video associated with the second video content data is accurate.2. The device of claim 1 , wherein the first video comprises a plurality of videos generated by a plurality of different media outlets.3. The device of claim 1 , wherein the processing of the digest comprises identifying a logo claim 1 , a watermark claim 1 , or any combination thereof included in the first video to identify at least one source of the first video.4. The device of claim 1 , wherein the digest identifies at least one source of the first video.5. The device of claim 1 , wherein the digest identifies a person included in the first video claim 1 , an object included in the first video claim 1 , a timestamp associated with the first video claim 1 , a ...

Подробнее
Номер записи: 27
03-02-2022 дата публикации

IMAGE/VIDEO ANALYSIS WITH ACTIVITY SIGNATURES

Номер: US20220036090A1
Автор: Migdal Joshua, Srinivasan Vikram
Принадлежит:

Video frames from a video are compressed into a single image or a single data structure that represents a unique visual flowprint or visual signature for a given activity being modeled from the video frames. The flowprint comprises a computed summary of the original pixel values associated with the video frames within the single image and the flowprint is specific to movements occurring within the video frames that are associated with the given activity. In an embodiment, the flowprint is provided as input to a machine-learning algorithm to allow the algorithm to perform object tracking and monitoring from the flowprint rather than from the video frames of the video, which substantially improves processor load and memory utilization on a device that executes the algorithm, and substantially improved responsiveness of the algorithm. 1. A method , comprising:obtaining video frames from a video;generating a single image from the video frames; andproviding the single image as a visual flowprint for an activity that was captured in the video frames.2. The method of claim 1 , wherein generating further includes tracking a region within each video frame associated with a modeled activity.3. The method of claim 2 , wherein identifying further includes obtaining pixel values for each video frame associated with points along an expected path of movement for the modeled activity within the region.4. The method of claim 3 , wherein obtaining the expected path further comprises determining an aggregated pixel value for each point along the expected path of movement across the video frames from the corresponding pixel values captured across the video frames for the corresponding point.5. The method of claim 4 , wherein determining further includes calculating the aggregated pixel value as an average of the corresponding pixel values across the video frames.6. The method of claim 4 , wherein determining further includes selecting the aggregated pixel value as a minimum pixel value ...

Подробнее
Номер записи: 28
03-02-2022 дата публикации

SYSTEM, METHOD AND DEVICE OPERABLE TO PRODUCE A VIDEO

Номер: US20220036091A1
Автор: Bornfreedom Power P., Smith-Bornfreedom Renato
Принадлежит:

A system, method and device operable to produce a video are disclosed herein. The system, method and device, in an embodiment, involve a recording session resulting in a video track. During the recording session, inputs are received at different points in time and a set of data markers are stored based on each one of the inputs. Each set has a first data marker and a second data marker, and the first data marker is chronologically located before the point in time of the input related to the set. Before or after the recording session, an additional input is received that is associated with an output. The output includes a visual output, an audio output or a combination thereof. A video is produced that has one or more desired portions of the video track. The video excludes at least one undesired portion of the video track, and the video includes the output or is otherwise playable to provide the output. 1. A method comprising:providing a plurality of computer-readable instructions that are executable to cause an electronic device to perform a plurality of steps, wherein the steps comprise:starting a recording session to record an event, wherein the recording of the event results in a video track; receiving a plurality of inputs at different points in time; and', 'in response to each one of the inputs, storing a set of timestamps associated with the input,', 'wherein each of the sets comprises a first timestamp and a second timestamp;', 'wherein the first timestamp of the set comprises a chronological position located before the point in time of the input associated with the set; and', 'wherein the chronological position depends on a time value stored before the recording session begins;, 'during the recording sessionbefore or after the recording session, receiving at least one additional input associated with an output, wherein the output comprises one of a visual output or an audio output; and the highlight video comprises one or more desired portions of the video ...

Подробнее
Номер записи: 29
03-02-2022 дата публикации

Fast video content matching

Номер: US20220036092A1
Автор: Albert Aparicio Isarn, Marc Junyent Martin, Miquel Angel Farre Guiu, Pablo Pernias
Принадлежит: Disney Enterprises Inc, Walt Disney Co Switzerland GmbH

A video content matching system includes a computing platform having a hardware processor and a memory storing a software code. When executed, the software code obtains a reference digital profile of a reference video segment, obtains a target digital profile of target video content, and compares the reference and target digital profiles to detect a candidate video segment of the target video content for matching to the reference video segment. The software code also frame aligns reference video frames of the reference video segment with corresponding candidate video frames of the candidate video segment to provide frame aligned video frame pairs, pixel aligns the frame aligned video frame pairs to produce frame and pixel aligned video frame pairs, and identifies, using the frame and pixel aligned video frame pairs, the candidate video segment as a matching video segment or a non-matching video segment for the reference video segment.

Подробнее
Номер записи: 30
21-01-2016 дата публикации

CONTENT PLAYBACK SYSTEM, SERVER, MOBILE TERMINAL, CONTENT PLAYBACK METHOD, AND RECORDING MEDIUM

Номер: US20160019425A1
Автор: YAMAJI Kei
Принадлежит:

Selected image data or specific information thereon is stored in association with moving image data as a management marker of a selected image. The selected image data is selected from among still image data extracted from the moving image data. When an output image of the selected image is captured, image analysis is performed on the captured image data to acquire a management marker of a captured image. A management marker of a selected image corresponding to the management marker of the captured image from among management markers of selected images stored in the storage is specified. Digest moving image data is generated by picking out a part of moving image data associated with the specific management marker. Control is performed so that a digest moving image is playbacked and displayed on the display section.

Подробнее
Номер записи: 31
18-01-2018 дата публикации

TECHNIQUES FOR ENHANCING CONTENT MEMORABILITY OF USER GENERATED VIDEO CONTENT

Номер: US20180018523A1
Автор: Angara Srinivasa Madhava Phaneendra, Kedia Manav, Shekhar Sumit, Shetty Akhil Sathyaprakash, Singal Dhruv
Принадлежит: ADOBE SYSTEMS INCORPORATED

Techniques are described for analyzing a video for memorability, identifying content features of the video that are likely to be memorable, and scoring specific content features within the video for memorability. The techniques can be optionally applied to selected features in the video, thus improving the memorability of the selected features. The features may be organic features of the originally captured video or add-in features provided using an editing tool. The memorability of video features, text features, or both can be improved by analyzing the effects of applying different styles or edits (e.g., sepia tone, image sharpen, image blur, annotation, addition of object) to the content features or to the video in general. Recommendations can then be provided regarding memorability score caused by application of the image styles to the video features. 1. A computer-implemented method for quantifying memorability of video content , the method comprising:receiving a video that comprises a plurality of video frames, wherein the video includes a video feature that is associated with a text feature, and wherein the text feature comprises textual content that is visually shown in at least one of the video frames;identifying the video feature and the associated text feature in the received video;determining a video feature score corresponding to the video feature, the video feature score indicating memorability of the video feature;determining a text feature score corresponding to the text feature, the text feature score indicating memorability of the text feature; anddetermining a content memorability score that is based on the video feature score and the text feature score.2. The computer-implemented method of claim 1 , further comprising causing display of a memorability map that:indicates a particular time period associated with a subset of the video frames in which the video feature and the text feature are visible; andincludes a visual indicator corresponding to ...

Подробнее
Номер записи: 32
18-01-2018 дата публикации

ACTIVATING A VIDEO BASED ON LOCATION IN SCREEN

Номер: US20180019002A1
Автор: McIntosh David, Pennello Chris
Принадлежит:

Providing a method for browsing portions of videos called video previews. The video previews may be associated with a link or predefined duration of a full video, such that the video preview is generated from a portion of the full video and viewed by a user. The video previews are configured to play a series of images associated with images from the portion of the full video when the video preview is activated. 119.-. (canceled)20. A method of browsing videos , the method comprising:receiving a video, wherein the video comprises a set of images;receiving, by a computing device, a frame object for displaying the video, wherein the set of images are played within the frame object when the frame object is located at a particular location on a display in a graphical user interface (GUI) of the computing device;displaying, by the computing device, a series of frame objects in the GUI, the series including the frame object, wherein the GUI allows motion of the frame objects in the GUI;identifying, by the computing device, that the frame object has moved to a particular location on the display in the GUI; andplaying, by the computing device, the video within the frame object in response to identifying that the frame object moves to a particular location on the display in the GUI.21. The method of claim 20 , wherein the video is a first video claim 20 , the frame object is a first frame object claim 20 , and the method further comprises:receiving a second video;receiving a second frame object for displaying the second video;displaying the second frame object next to the first frame object in the GUI; andin response to identifying that the second frame object is located at the particular location on the display in the GUI of the computing device, playing the second video within the second frame object.22. The method of claim 21 , further comprising stopping the first video from playing when the second frame object is located at the particular location on the display in the ...

Подробнее
Номер записи: 33
28-01-2016 дата публикации

ANATOMICAL SITE RELOCALISATION USING DUAL DATA SYNCHRONISATION

Номер: US20160022125A1
Автор: MARESCAUX Jacques, NICOLAU Stephane, SOLER Luc, Vemuri Anant Suraj
Принадлежит:

A method and a system for anatomical site relocalisation using dual data synchronisation. Method for repositioning, possibly several times, at a specific location, which has been already explored during a first or “reference exploration”, a flexible endoscope during one or more successive endoluminal or extraluminal subsequent or “new exploration”, or similar procedures, wherein the repositioning is realized either manually, by a human user, or automatically, by a robotic system, from or by way of a synchronisation process between a “new exploration” flexible endoscope video and the “reference exploration” flexible endoscope video displayed in parallel on or in two different windows, on one or more screens. 120-. (canceled)21. Method for repositioning , possibly several times , at a specific location , which has been already explored during a first or “reference exploration” , a flexible endoscope during one or more successive endoluminal or extraluminal subsequent or “new exploration” , or similar procedures , wherein the repositioning is realized either manually , by a human user , or automatically , by a robotic system , from or by means of a synchronisation process between a “new exploration” flexible endoscope video and the “reference exploration” flexible endoscope video displayed in parallel on or in two different windows , on one or more screens.22. Method according to claim 21 , wherein the synchronisation process is based only on the position and orientation registration of the end tip of the flexible endoscope recorded during the first or reference exploration and a subsequent or new exploration from a tracking device claim 21 , providing the location and orientation of said end tip of the endoscope according to a fixed external reference frame such as an electro-magnetic claim 21 , fiberoptic or any other similar type of tracking device.23. Method according to claim 21 , wherein the synchronisation process is based on the position and orientation ...

Подробнее
Номер записи: 34
03-02-2022 дата публикации

INTELLIGENT COMMENTARY GENERATION AND PLAYING METHODS, APPARATUSES, AND DEVICES, AND COMPUTER STORAGE MEDIUM

Номер: US20220038790A1
Автор: Chen Qi, DUAN Hong, OUYANG Caisheng, ZHENG Yang
Принадлежит:

The present disclosure provides an intelligent commentary generation method. The method includes: obtaining a match data stream; parsing the match data stream, to obtain candidate events from the match data stream; determining events from the candidate events, to generate a sequence of events; and generating commentary scripts corresponding to the match data stream according to the sequence of events. 1. An intelligent commentary generation method , applied to an intelligent commentary generation device , the method comprising:obtaining a match data stream;parsing the match data stream, to obtain candidate events from the match data stream;determining events to from the candidate events to, to generate a sequence of events to; andgenerating commentary scripts corresponding to the match data stream according to the sequence of events.2. The method according to claim 1 , wherein determining the events comprises:obtaining time periods in which the candidate events occur and importance degree parameters of the candidate events;determining, based on the time periods in which the candidate events occur, sets of candidate events to corresponding to the time periods; anddetermining, based on the importance degree parameters of the candidate events, events corresponding to the time periods from the sets of candidate events corresponding to the time periods, to obtain the sequence of events.3. The method according to claim 1 , wherein generating the commentary scripts corresponding to the match data stream comprises:obtaining attribute information of each event in the sequence of events, wherein the attribute information includes at least a place where the event occurs and character information corresponding to the event;obtaining a commentary content generation strategy corresponding to each event;generating commentary texts based on the commentary content generation strategies and the attribute information; andgenerating, based on the commentary texts, the commentary ...

Подробнее
Номер записи: 35
21-01-2021 дата публикации

SYSTEMS AND METHODS FOR EDITING VIDEOS BASED ON MOTION

Номер: US20210020201A1
Автор: Patry Jean
Принадлежит:

Motion within first video content and second video content may be assessed. A match between the motions assessed within the first video content and the second video content may be determined. The match may include a first set of video frames within the first video content and a second set of video frames within the second video content within which the matching motion is present. A first video portion (including frame(s) of the first set of video frames) of the first video content and a second video portion (include frame(s) of the second set of video frames) of the second video content may be identified based on the match. The first video portion and the second video portion may be concatenated to provide a transition between the first video portion and the second video portion in which continuity of motion may be achieved. 1. A system for editing videos based on motion , the system comprising: access video information defining video content;', 'assess motion within the video content;', 'determine a match between the motion assessed within at least two portions of the video content, the match including sets of video frames within the at least two portions of the video content within which the matching motion is present;', 'identify video portions within the video content based on the match, individual ones of the video portions including at least some of video frames of the sets of video frames within which the matching motion is present;', 'concatenate the video portions such that at least two sets of the at least some of the video frames of the sets of video frames are adjacent, the concatenation of the video portions resulting in at least one transition between the video portions in which continuity of motion is achieved., 'one or more physical processors configured by machine-readable instructions to2. The system of claim 1 , wherein the motion assessed within the video content includes capture motion of the video content.3. The system of claim 2 , wherein the ...

Подробнее
Номер записи: 36
16-01-2020 дата публикации

METHOD AND SYSTEM OF MULTIPLE CHANNEL VIDEO CODING WITH CROSS-CHANNEL REFERENCING

Номер: US20200021813A1
Автор: Aristarkhov Vasily, Tanner Jason
Принадлежит: Intel Corporation

Techniques related to video coding include multiple channel video coding with cross-channel referencing. 1. A device for video coding comprising:memory to store at least one video; and generating multiple video sequences of the same image content of a video wherein the individual video sequences each have a different resolution, different bitrate, or both, and a bitrate-related value;', 'determining whether the multiple video sequences comprise at least one source video sequence matched to at least one sink video sequence of the multiple video sequences depending at least on comparisons among the bitrate-related values; and', 'encoding the at least one sink video sequence using at least one encode control that restricts encode decisions to encode the sink video sequence depending on encode decisions previously established for a matching source video sequence., 'at least one processor communicatively coupled to the memory and being arranged to operate by2. The device of claim 1 , wherein the bitrate-related value is a quantization parameter (QP) or a quantization step value.3. The device of claim 1 , wherein the at least one processor being arranged to operate by determining whether each possible pair of video sequences is a match without being limited to resolution of the video sequences to make the matches.4. The device of claim 1 , wherein the at least one processor being arranged to operate by determining a source video sequence matches a sink video sequence at least when the difference between the bitrate-related values of two of the video sequences is below a threshold.5. The device of claim 1 , wherein at least one source video sequence is matched to multiple sink video sequences.6. The device of claim 1 , wherein at least one video sequence is not matched to any other video sequence while at least one other video sequence is matched to another video sequence.7. The device of claim 1 , wherein a bitrate-related value of a video sequence closest to a mean claim ...

Подробнее
Номер записи: 37
21-01-2021 дата публикации

SYSTEM OF AUTOMATIC CREATION OF A SCENARIO VIDEO CLIP WITH A PREDEFINED OBJECT

Номер: US20210021912A1
Автор: GURICHEV Dmitry Vyacheslavovich, KALINICHENKO Denis Evgenyevich, KLYUEV Sergey Sergeevich, ROZHENKOV Anton Vladimirovich
Принадлежит:

A system for automatic creation a scenario video clip with a predefined object or a group of objects in the frame comprises: a shooting unit, a data storage module, a predefined object or a group of objects identification in primary video data unit; an object or a group of objects data input unit for their identification; provided that the system in addition comprises: a relevant video data retrieval unit with the predefined object or the group of objects in the frame; a relevant video data processing unit; at least one scenario pattern including data set for operation of shooting unit, retrieval unit and processing unit. 1. A system for automatic creation of a scenario video clip with a predefined object or a group of objects in the frame comprising:a shooting unit, including at least one primary video data recorder;a data storage module, including primary video data storage unit;a predefined object or a group of objects identification in primary video data unit;a predefined object or group of objects data input unit for their identification;characterized in that it additionally comprises:a relevant video data retrieval unit with the predefined object or the group of objects in the frame, wherein the relevant video data are understood as video segments with the predefined object in the frame cut out from the primary video data using the marks put by the identification unit;a relevant video data processing unit;at least one scenario pattern including data set for operation of the shooting unit, relevant video data retrieval unit and relevant video data processing unit,wherein, each recorder of the primary video data from the shooting unit operates according to the scenario pattern data, which in terms of the shooting unit operation is the data specifying frame view, depth, frame geometry, objective field of view, camera movement, predefined object zooming in/out in the frame;wherein, the relevant video data retrieval unit includes software which enables to cut out ...

Подробнее
Номер записи: 38
26-01-2017 дата публикации

System for Automatically Editing Video

Номер: US20170024614A1
Автор: Sanil Rohan, Wang Jinjun
Принадлежит:

A system provides automated editing of a media file. Frames of a media file are extracted and feature vectors are generated based thereon. The feature vectors are clustered according to similarity of the content of the feature vectors and the temporal proximity of frames corresponding to the feature vectors in the media file. Clusters are ranked and selected according to the ranking. Segments of the media file corresponding to the selected clusters are combined into a highlight video. Hotspots in a media file may be identified in a media file by detecting local maxima in a measure of movement of pixels between frames. Clusters may be ranked and selected according to an iterative algorithm that identifies clusters that are the most different from an average of the feature vectors and from other selected clusters. 1. A method comprising:receiving, by a computer system, an input media file;for each frame of a plurality of frames corresponding to the input media file, identifying a feature vector for the each frame;identifying, by the computer system, a plurality of clusters of feature vectors from the feature vectors for the plurality of frames;ranking, by the computer system, the plurality of clusters of feature vectors;selecting, by the computer system, a set of clusters from the plurality of clusters of feature vectors according to the ranking; andgenerating, by the computer system, a highlight video including segments of the media file, each segment including frames corresponding to the feature vectors of one of the clusters of the set of clusters.2. The method of claim 1 , wherein ranking claim 1 , by the computer system claim 1 , the plurality of clusters of feature vectors comprises ranking each cluster according to energy within a video segment of the media file including frames corresponding to the feature vectors of the each cluster.3. The method of claim 2 , wherein the energy within a video segment is a function of variance within the video segment.4. The ...

Подробнее
Номер записи: 39
26-01-2017 дата публикации

Image processing method

Номер: US20170024626A1
Автор: Yasushi Inaba
Принадлежит: Canon Imaging Systems Inc

An image processing method for a picture of a participant, photographed in an event, such as a marathon race, increases the accuracy of recognition of a race bib number by performing image processing on a detected race bib area, and associates the recognized race bib number with a person included in the picture. This image processing method detects a person from an input image, estimates an area in which a race bib exists based on a face position of the detected person, detects an area including a race bib number from the estimated area, performs image processing on the detected area to thereby perform character recognition of the race bib number from an image subjected to image processing, and associates the result of character recognition with the input image.

Подробнее
Номер записи: 40
28-01-2016 дата публикации

Activity identification in video

Номер: US20160026874A1
Автор: Jonathan Taylor, Nick Hodulik
Принадлежит: GoPro Inc

Video and corresponding metadata is accessed. Events of interest within the video are identified based on the corresponding metadata, and best scenes are identified based on the identified events of interest. A video summary can be generated including one or more of the identified best scenes. The video summary can be generated using a video summary template with slots corresponding to video clips selected from among sets of candidate video clips. Best scenes can also be identified by receiving an indication of an event of interest within video from a user during the capture of the video. Metadata patterns representing activities identified within video clips can be identified within other videos, which can subsequently be associated with the identified activities.

Подробнее
Номер записи: 41
28-01-2016 дата публикации

VIDEO COMPARISON USING COLOR HISTOGRAMS

Номер: US20160026891A1
Автор: Lee Morris
Принадлежит:

Methods, apparatus and articles of manufacture for video comparison using color histograms are disclosed. Example methods disclosed herein to compare video sequences include determining a color histogram corresponding to an input video sequence based on color values of pixels sampled from a plurality of video frames of the input video sequence. Such disclosed example methods also include adjusting the color histogram corresponding to the input video sequence based on a first reference color histogram corresponding to a first reference video sequence different from the input video sequence to determine an adjusted color histogram corresponding to the input video sequence. Such disclosed example methods further include comparing the adjusted color histogram and the first reference color histogram to determine whether the first reference video sequence matches the input video sequence. 1. A method to compare video sequences , the method comprising:determining, with a processor, a color histogram corresponding to an input video sequence based on color values of pixels sampled from a plurality of video frames of the input video sequence;adjusting, with the processor, the color histogram corresponding to the input video sequence based on a first reference color histogram corresponding to a first reference video sequence different from the input video sequence to determine an adjusted color histogram corresponding to the input video sequence; andcomparing, with the processor, the adjusted color histogram and the first reference color histogram to determine whether the first reference video sequence matches the input video sequence.2. The method as defined in claim 1 , wherein the adjusting of the color histogram includes:multiplying bin values of the color histogram corresponding to the input video sequence by a scale factor to determine scaled bin values of the color histogram corresponding to the input video sequence; anddetermining bin values of the adjusted color ...

Подробнее
Номер записи: 42
26-01-2017 дата публикации

MOBILE TERMINAL AND CONTROL METHOD FOR THE SAME

Номер: US20170025151A1
Автор: AN Shounan, Baek Seungmin, HAN Jongwoo, LEE Jungho
Принадлежит: LG ELECTRONICS INC.

Disclosed are a mobile terminal and a method for controlling the same. The mobile terminal includes: a memory capable of storing video data therein; a touch screen capable of receiving a touch input related to the video data; and a controller capable of reducing a play time or a capacity of the video data based on a preset reference, such that a summary of the video data is generated based on the touch input, wherein the preset reference is established based on a restriction condition of a social network service or an application for sharing the video data. 1. A mobile terminal , comprising:a memory capable of storing video data therein;a touch screen capable of receiving a touch input related to the video data; anda controller capable of reducing a play time or a capacity of the video data based on a preset reference, such that a summary of the video data is generated based on the touch input,wherein the preset reference is established based on a restriction condition of a social network service or an application for sharing the video data.2. The mobile terminal of claim 1 , wherein the controller extracts intra-coded frames from the video data at preset time intervals claim 1 , and generates a summary of the video data based on the extracted frames.3. The mobile terminal of claim 2 , wherein the controller analyzes images of the extracted frames claim 2 , and sets an interest region included in the summary of the video data based on a result of the analysis.4. The mobile terminal of claim 2 , wherein the controller detects information related to a person's face from the images of the extracted frames claim 2 , and generates the summary of the video data based on the detected information.5. The mobile terminal of claim 1 , wherein an image related to the video data is output to the touch screen claim 1 , andwherein the controller executes a function related to play of the video data in response to a first touch input applied to the image, and executes a function ...

Подробнее
Номер записи: 43
28-01-2016 дата публикации

SCENE AND ACTIVITY IDENTIFICATION IN VIDEO SUMMARY GENERATION

Номер: US20160027470A1
Автор: Newman David A., Silver Adam
Принадлежит:

Video and corresponding metadata is accessed. Events of interest within the video are identified based on the corresponding metadata, and best scenes are identified based on the identified events of interest. A video summary can be generated including one or more of the identified best scenes. The video summary can be generated using a video summary template with slots corresponding to video clips selected from among sets of candidate video clips. Best scenes can also be identified by receiving an indication of an event of interest within video from a user during the capture of the video. Metadata patterns representing activities identified within video clips can be identified within other videos, which can subsequently be associated with the identified activities. 1. A method for identifying scenes in captured video for inclusion in a video summary , the method comprising;accessing metadata associated with a video, the accessed metadata representative of capture of the video;identifying a plurality of events of interest within the video based on the accessed metadata;for each identified event of interest, identifying a best scene in the video associated with the identified event of interest, the identified best scene comprising a threshold amount of video occurring before and after a video frame or portion corresponding to the identified event of interest; andselecting one or more identified best scenes for inclusion in a video summary.2. The method of claim 1 , further comprising:receiving a request for a video summary from the user; andgenerating a video summary including a plurality of selected best scenes.3. The method of claim 2 , wherein generating the video summary comprises concatenating the plurality of selected best scenes.4. The method of claim 1 , wherein the accessed metadata is generated by a camera during the capture of the video.5. The method of claim 4 , wherein the accessed metadata comprises telemetry data describing a motion of the camera during ...

Подробнее
Номер записи: 44
25-01-2018 дата публикации

SYSTEM AND METHOD FOR PROVIDING SURVEILLANCE DATA

Номер: US20180025231A1
Автор: JEON Seoung Seon, LIM Jeong Eun, NOH Seung In
Принадлежит: HANWHA TECHWIN CO., LTD.

A system and method for providing surveillance data are provided. The system includes: a pattern learner configured to learn a time-based data pattern by analyzing at least one of image data of one or more images and sound data of sound obtained from a surveillance zone at a predetermined time or time period, and to generate an event model based on the time-based data pattern; and an event detector configured to detect at least one event by comparing the event model with a time-based data pattern of at least one of first image data of one or more first images and first sound data of first sound obtained from the surveillance zone. 1. A system for providing surveillance data , the system comprising at least one processor to implement:a pattern learner configured to learn a time-based data pattern by analyzing at least one of image data of one or more images and sound data of sound obtained from a surveillance zone at a predetermined time or time period, and to generate an event model based on the time-based data pattern; andan event detector configured to detect at least one event by comparing the event model with a time-based data pattern of at least one of first image data of one or more first images and first sound data of first sound obtained from the surveillance zone.2. The system of claim 1 , wherein the pattern learner comprises:a first learner configured to calculate a statistical data value of at least one of a color, a number of at least one object detected in the surveillance zone, and a degree of movement of the detected at least one object from the one or more images; anda second learner configured to calculate a statistical data value of at least one sound level from the sound,wherein the time-based data pattern corresponds to a time-based variation in the statistical value calculated by the first learner or the second learner.3. The system of claim 2 , wherein the pattern learner is configured to generate the event model based on the image data and ...

Подробнее
Номер записи: 45
10-02-2022 дата публикации

Method for generating clipping template, and electronic device

Номер: US20220044026A1
Автор: Weibin Huang
Принадлежит: Beijing Dajia Internet Information Technology Co Ltd

A method for generating a clipping template is provided. In the method, clipping information of a target multimedia resource is acquired in response to a template generation request for the target multimedia resource, wherein the clipping information includes at least one of clip operation information or clipping material information; clipping information conforming to a target type is selected from the clipping information of the target multimedia resource, and template data is determined based on the selected clipping information; and a clipping template is generated based on the template data.

Подробнее
Номер записи: 46
24-01-2019 дата публикации

ASSOCIATING STILL IMAGES AND VIDEOS

Номер: US20190026268A1
Автор: Adam Hartwig, Gargi Ullas, Jing Yushi, Rowley Henry Allan, Song Yang, Zhao Ming
Принадлежит:

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for associating still images and videos. One method includes receiving a plurality of images and a plurality of videos and determining whether the images are related to the videos. The determining includes, for an image and a video, extracting features from the image and extracting features frames of the video, and comparing the features to determine whether the image is related to the video. The method further includes maintaining a data store storing data associating each image with each video determined to be related to the image. 1. (canceled)2. A system , comprising: receiving a digital image and a digital video;', 'extracting one or more features from the digital image;', 'identifying one or more representative frames in the digital video, wherein each representative frame is representative of a portion of the digital video;', 'extracting one or more respective features from each representative frame;', 'comparing the one or more features extracted from the digital image to the one or more respective features extracted from each representative frame; and', 'classifying the digital image as related to the digital video based on the comparison of the one or more features extracted from the image to the one or more respective features extracted from each representative frame., 'one or more computers including one or more storage devices storing instructions that when executed by the one or more computers cause the one or more computers to perform operations comprising3. The system of claim 2 , wherein the digital image is a digital still image.4. The system of claim 2 , wherein classifying the digital image as related to the digital video comprises:determining a strength of relationship between the digital image and the digital video based on the comparison of the one or more features extracted from the image to the one or more respective features extracted from each ...

Подробнее
Номер записи: 47
28-01-2016 дата публикации

GENERATING VIDEO SUMMARIES FOR A VIDEO USING VIDEO SUMMARY TEMPLATES

Номер: US20160029105A1
Автор: Newman David A., Schunck Brian G.
Принадлежит:

Video and corresponding metadata is accessed. Events of interest within the video are identified based on the corresponding metadata, and best scenes are identified based on the identified events of interest. A video summary can be generated including one or more of the identified best scenes. The video summary can be generated using a video summary template with slots corresponding to video clips selected from among sets of candidate video clips. Best scenes can also be identified by receiving an indication of an event of interest within video from a user during the capture of the video. Metadata patterns representing activities identified within video clips can be identified within other videos, which can subsequently be associated with the identified activities. 1. A method for generating a video summary using a video summary template , the method comprising:receiving a request for a video summary of one or more videos;selecting a video summary template for use in generating the video summary, the video summary template comprising a plurality of template slots;identifying, for each template slot, a set of candidate video clips associated with the template slot;selecting, for each template slot, an associated candidate video clip from the set of candidate video clips associated with the template slot; andgenerating the video summary by replacing each template slot in the video summary template with the associated selected candidate video clip.2. The method of claim 1 , wherein a template slot specifies one or more video clip requirements claim 1 , and wherein each video clip in the set of candidate video clips associated with the template slot satisfy the specified video clip requirements.3. The method of claim 1 , wherein a template slot specifies a video clip length claim 1 , and wherein each video clip in the set of candidate video clips associated with the template slot is the specified video clip length.4. The method of claim 1 , wherein identifying a set of ...

Подробнее
Номер записи: 48
24-01-2019 дата публикации

ACTOR/PERSON CENTRIC AUTO THUMBNAIL

Номер: US20190026563A1
Автор: Pachauri Kulbhushan
Принадлежит:

Approaches, techniques, and mechanisms are disclosed for generating thumbnails. According to one embodiment, a subset of images each depicting character face(s) is identified from a collection of images. An unsupervised learning method is applied to automatically cluster the subset of images into image clusters. Top image clusters are selected from the image clusters based at least in part on weighted scores of images clustered within the image clusters. Thumbnail(s) are generated from images in the top image clusters. 1. A method comprising:receiving, from a media bitstream, a collection of images and non-visual information accompanying the collection of images;applying one or more computer-implemented face detection methods to analyze visual information in the collection of images received in the media bitstream;analyzing audio information in the non-visual information, as received from the media bitstream, which accompanies the collection of images in the media bitstream;using analytical results of the visual information and the audio information in the non-visual information in connection with the collection of images to identify, from the collection of images, a subset of images each depicting one or more character faces;automatically clustering the subset of images into a plurality of image clusters;selecting one or more top image clusters from the plurality of image clusters based at least in part on weighted scores of images clustered within the plurality of image clusters;generating one or more thumbnail images from one or more images in the one or more top image clusters;causing the one or more thumbnail images to be rendered on a display device to a viewer.2. The method of claim 1 , wherein the collection of images represents one or more of: a series of video images claim 1 , a plurality of still photographic images claim 1 , a plurality of computer-rendered images claim 1 , or a combination of video images and still photographic images.3. The method of ...

Подробнее
Номер записи: 49
24-01-2019 дата публикации

METHOD AND SYSTEM FOR DETECTING AN UNOCCUPIED REGION WITHIN A PARKING FACILITY

Номер: US20190027037A1
Автор: Lehn Andreas, NORDBRUCH Stefan
Принадлежит:

A method for detecting an unoccupied region within a parking facility, using at least one environment sensor disposed in a stationary manner within the parking facility, is furnished, at least encompassing the following: sensing measured data of at least one segment of the parking facility by way of at least one environment sensor; comparing the measured data with reference measured data in order to recognize a change in the segment of the parking facility; and detecting the segment as an unoccupied or non-unoccupied region as a function of the recognition of a change. 1. A method for detecting an unoccupied region within a parking facility using at least one environment sensor disposed in a stationary manner within the parking facility , the method comprising:sensing measured data of at least one segment of the parking facility by at least one environment sensor;comparing the measured data with reference measured data to recognize a change in the segment of the parking facility; anddetecting the segment as an unoccupied or non-unoccupied region as a function of the recognition of a change.2. The method of claim 1 , wherein at least two environment sensors are used claim 1 , a segment of the parking facility being sensed by at least two of the environment sensors which are configured differently from one another and/or which implement measurement principles that are different from one another.3. The method of claim 1 , wherein at least two environment sensors are used claim 1 , for each of the environment sensors:measured data of the segment of the parking facility being sensed by the environment sensor;the respective measured data are compared with reference measured data associated with the respective environment sensor, a change is recognized for each environment sensor; andthe segment is detected as an unoccupied region as a function of whether no change is recognized for a specific number of the environment sensors.4. The method of claim 3 , wherein the segment ...

Подробнее
Номер записи: 50
25-01-2018 дата публикации

METHOD AND APPARATUS FOR INTEGRATED TRACKING OF VISITORS

Номер: US20180027383A1
Автор: Andreatta Sebastian, Fathi Nader, Hagen Klaus ten, Seidman Glenn R.
Принадлежит:

System and method for tracking a mobile device includes: receiving unique identifications for a mobile device; filtering out the unique identifications to obtain a true identifications for the mobile device; identifying cameras relevant to movement of the mobile device; receiving video streams; generating data structures for the video streams and tracking information of the mobile device, the data structure including time stamped videos, and viewpoints of the identified cameras; utilizing the data structures to retrieve, video and tracking information for the mobile device and the user, as the mobile moves in the site; and applying analytics to the retrieved video and tracking information to analyze behavior of the user and to predict what the user will do while on site. 1. A method for tracking a mobile device in a site , the method comprising:receiving, in real time, a plurality of unique identifications for a mobile device vising the site;filtering out the plurality of unique identifications for the mobile device to obtain a true identifications for the mobile device;in real time, identifying cameras relevant to movement of the mobile device responsive to the true identifications for the mobile device;receiving video streams of the movement of the mobile device from the identified cameras, time stamping the received video streams and storing the time stamped video streams in a computer storage medium;generating data structures for the video streams and tracking information of the mobile device, the data structure including time stamped videos, and viewpoints of the identified cameras;utilizing the data structures to retrieve, in real time, video and tracking information for the mobile device and the user, as the mobile moves in the site; andapplying analytics to the retrieved video and tracking information to analyze behavior of the user and to predict what the user will do while on site.2. The method of claim 1 , wherein the data structures further include a ...

Подробнее
Номер записи: 51
24-01-2019 дата публикации

COGNITIVE DYNAMIC VIDEO SUMMARIZATION USING COGNITIVE ANALYSIS ENRICHED FEATURE SET

Номер: US20190027188A1
Автор: AKOLKAR RAHUL P., Block Alexander M., Chanchlani Manali J., Farinelli Kristi A.
Принадлежит:

Accurate and concise summarization of a media production is achieved using cognitive analysis which groups segments of the production into clusters based on extracted features, selects a representative segment for each cluster, and combines the representative segments to form a summary. The production is separated into a video stream, a speech stream and an audio stream, from which the cognitive analysis extracts visual features, textual features, and aural features. The clustering groups segments together whose visual and textual features most closely match. Selection of the representative segments derives a score for each segment based on factors including a distance to a centroid of the cluster, an emotion level, an audio uniqueness, and a video uniqueness. Each of these factors can be weighted, and the weights can be adjusted in accordance with user input. The factors can have initial weights which are based on statistical attributes of historical media productions. 1. A method of providing a summary of a media production comprising:receiving the media production in computer-readable form, by executing first instructions in a computer system;dividing the media production into original segments having respective time stamps indicating a time order of the original segments, by executing second instructions in the computer system;conducting a cognitive analysis of each of the original segments to extract at least one cognitive feature associated with each original segment, by executing third instructions in the computer system;grouping the original segments into multiple clusters based on the cognitive features by identifying one or more predominant features for each given cluster based on segments making up the given cluster, by executing fourth instructions in the computer system;selecting a representative segment for each of the clusters based on one or more selection factors which include a distance of a given segment to a centroid of its corresponding cluster, ...

Подробнее
Номер записи: 52
23-01-2020 дата публикации

Analysis of Operator Behavior Focalized on Machine Events

Номер: US20200026927A1
Автор: Gonzalez-Banos Hector H., Narasimha Ramya
Принадлежит:

A system and method for analyzing behavior in a video is described. The method includes extracting a plurality of salient fragments of a video; associating a time anchor with an occurrence of a first machine event of a machine operated by a human subject; generating a focalized visualization, based on the time anchor, from one or more of the plurality of salient fragments of the video; tagging the human subject in the focalized visualization with a unique identifier; and analyzing behavior of the human subject, using the focalized visualization, to generate a behavior score associated with the unique identifier and the first machine event. 1. A computer-implemented method comprising:extracting a plurality of salient fragments of a video;associating a time anchor with an occurrence of a first machine event of a machine operated by a human subject;generating a focalized visualization, based on the time anchor, from one or more of the plurality of salient fragments of the video;tagging the human subject in the focalized visualization with a unique identifier; andanalyzing behavior of the human subject, using the focalized visualization, to generate a behavior score associated with the unique identifier and the first machine event.2. The computer-implemented method of claim 1 , further comprising:storing the behavior score as a record in a database using the unique identifier and the first machine event as attributes.3. The computer-implemented method of claim 2 , further comprising:performing a query on the database based on selection criteria that is selected from the group consisting of date of record, unique identifier, time anchor, first machine event, behavior score, minimum behavior score, maximum behavior score, and average behavior score.4. The computer-implemented method of claim 1 , further comprising:generating a baseline behavior for a behavioral attribute; andproducing a contrastive behavior score by comparing the behavior of the human subject to the ...

Подробнее
Номер записи: 53
28-01-2021 дата публикации

DATA PROCESSING SYSTEMS FOR REAL-TIME CAMERA PARAMETER ESTIMATION

Номер: US20210027493A1
Автор: Citraro Leonardo, Dubout Charles Xavier Quentin, Fua Pascal, Hasfura Andres Michael Levering, Jayaram Vivek, Neila Pablo Márquez, Renaut Felix Constant Marc, Savarè Stefano, Shitrit Horesh Beny Ben
Принадлежит:

Data processing systems are disclosed for determining semantic and person keypoints for an environment and an image and matching the keypoints for the image to the keypoints for the environment. A homography is generated based on the keypoint matching and decomposed into a matrix. Camera parameters are then determined from the matrix. A plurality of random camera poses can be generated and used to project keypoints for an environment using image keypoints. The projected keypoints can be compared to the actual keypoints for the environment to determine an error and weighting for each of the random camera poses. 1. A system comprising:one or more computer processors configured as a neural network; and training the neural network to locate and identify semantic keypoints in an image sequence corresponding to keypoints in an environment, wherein each keypoint of the keypoints in the environment has a known location;', 'training the neural network to locate and identify person keypoints in the image sequence corresponding to the keypoints in the environment;', 'matching each semantic keypoint of the semantic keypoints in the image sequence to a respective semantic keypoint of the keypoints in the environment;', 'matching each person keypoint of the person keypoints in the image sequence to a respective person keypoint of the keypoints in the environment;', 'generating a homography for each image in the image based on the matching of each of the semantic keypoints in the image sequence to the respective semantic keypoint in the environment and the matching of each of the person keypoints in the image sequence to the respective person keypoint in the environment; and', 'determining a camera parameter based on the homography., 'memory storing computer-executable instructions that, when executed by the one or more computer processors, cause the one or more computer processors to perform operations comprising2. The system of claim 1 , wherein determining the camera parameter ...

Подробнее
Номер записи: 54
23-01-2020 дата публикации

Camera Capture in an Organization Information Distribution System

Номер: US20200029133A1
Автор: Gehlsen John Michael, Jarvis Jeffrey Brian, Kogut Joseph Alan
Принадлежит: NRS Systems

Techniques described herein provide video capture via an organization information distribution system. In implementations, a video monitoring device connects to a camera over a network and obtains video data associated with a live video stream. Some implementations store the video data in a circular buffer. In response to receiving a trigger event, one or more implementations generate a video clip from the video data in the circular buffer, where the video clip includes video data stored prior to the trigger event. In turn, one or more implementations transmit the video clip to a destination computing device. 1. A device comprising:one or more processor; and connecting, over a network, to a camera via a video monitoring device;', 'obtaining, from the camera, video data associated with a live video stream;', 'storing the video data in a circular buffer;', 'receiving a trigger event associated with an organization information distribution system;', 'generating a video clip from the video data in the circular buffer based on the trigger event, the video clip including video data stored prior to the trigger event, and', 'transmitting the video clip to a destination computing device via the organization information distribution system., 'one or more memory storage devices storing processor executable instructions that, responsive to execution by the one or more processors, cause the device to perform operations comprising2. The device as recited in claim 1 , wherein generating the video clip comprises:extracting a first amount of the video data prior to the trigger event from the circular buffer based on a first predetermined extraction value;extracting a second amount of the video data after the trigger event from the circular data based on a second predetermined extraction value; andcombining the first amount of the video data with the second amount of the video data to generate the video clip.3. The device as recited in claim 1 , wherein said receiving the trigger ...

Подробнее
Номер записи: 55
28-01-2021 дата публикации

AUTOMATIC PERSONALIZED STORY GENERATION FOR VISUAL MEDIA

Номер: US20210029389A1
Автор: Guo Shengbo, ZHANG YING
Принадлежит:

Exemplary embodiments relate to the automatic generation of captions for visual media, including photos, photo albums, non-live video, and live video. The visual media may be analyzed to determine contextual information (such as location information, people and objects in the video, time, etc.). A system may integrate this information with information from the user's social network and a personalized language model built using public-facing language from the user. The personalized language model captures the user's way of speaking to make the generated captions more detailed and personalized. The language model may account for the context in which the video was generated. The captions maybe used to simplify and encourage content generation, and may also be used to index visual media, rank the media, and recommend the media to users likely to engage with the media. 1. A method , comprising:receiving a request to generate a personalized language model configured to reflect a personal narrative style of the user;retrieving public-facing language associated with the first user;using the public-facing language to build the personalized language model, the personalized language model reflecting a vocabulary, a sentence or phrase structure, and a sentence construction specific to the user;accessing visual media;analyzing information associated with the visual media to identify a context of the visual media;providing the context to the personalized language model; andgenerating a caption for the visual media in the user's personal narrative style using the personalized language model and the context.2. The method of claim 1 , wherein the request to generate the personalized language model includes representative target language claim 1 , and the representative target language is used to supplement the retrieved public facing language.3. The method of claim 1 , wherein some of the public-facing language is machine-generated language claim 1 , and the machine-generated ...

Подробнее
Номер записи: 56
28-01-2021 дата публикации

Computing System with Content-Characteristic-Based Trigger Feature

Номер: US20210029417A1
Автор: Dimitriou Konstantinos Antonios, Harron Wilson
Принадлежит:

In one aspect, an example method includes (i) receiving, by a computing system, media content; (ii) generating, by the computing system, a fingerprint of a portion of the received media content; (iii) determining, by the computing system, that the received media content has a predefined characteristic; (iv) responsive to determining that the received media content has the predefined characteristic, transmitting, by the computing system, the generated fingerprint to a content identification server to identify the portion of the received media content; and (v) performing an action based on the identified portion of media content. 1. A method comprising:determining, by a computing system, that a first portion of media content and a second portion of the media content lack a threshold extent of similarity with each other;responsive to determining the first portion and the second portion lack the threshold extent of similarity with each other, transmitting, by the computing system, a fingerprint associated with the second portion of the media content to a content identification server to identify the second portion of the media content; andperforming an action based on an identified second portion of the media content.2. The method of claim 1 , further comprising receiving the media content from a receiver connected to the computing system.3. The method of claim 1 , wherein the computing system receives the first portion before receiving the second portion.4. The method of claim 1 , wherein (i) the first portion is a program segment and the second portion is a commercial claim 1 , (ii) the first portion is a first commercial and the second portion is a second commercial that is different from the first commercial claim 1 , (iii) the first portion is a commercial and the second portion is a program segment claim 1 , or (iv) the first portion is a first program segment and the second portion is a second program segment that is different from the first program segment.5. ...

Подробнее
Номер записи: 57
04-02-2016 дата публикации

VIDEO SEARCH AND PLAYBACK INTERFACE FOR VEHICLE MONITOR

Номер: US20160034477A1
Автор: MAO Shulin, WU Liyun, XUE Mingshao
Принадлежит:

A method and apparatus including a plurality of video recordings in a database containing images of vehicles traveling within a predetermined geographic area and a list of license plates attached to each of those vehicles, a display the depicts a map of the geographic area, an input that receives an identifier of a license plate of a vehicle and a time period and a processor that searches the plurality of video recordings for the license plate, returns a list of cameras capturing images of the identified license plate, sorts the returned list by time of capture and displays a motion path of the vehicle on the map for the time period based upon the returned list. The method and apparatus may also include a uniform interface where the end-user can click the camera mark on the vehicle motion path to playback historic video recorded by this camera individually or click the whole motion path to playback a merged video which combines all recorded video from returned cameras into one display using only one window for the display of the merged video. 1. A method comprising:providing a database, the database containing map and road information in a monitored area, location information for a plurality of cameras, video clips of the monitored area recorded by each of the plurality of cameras and a list of automobile license plate numbers including a location and time of capture of each license plate detected within the plurality of video clips;an input of a computer system receiving a specified license plate number of an automobile and an identifier of a time period;a processor of the computer system searching the database for all cameras that captured the specified license plate number in the specified time period and returning a list of cameras;a processor of the computer system sorting the returned cameras by time of detection of the specified license plate and drawing a motion path associated with the specified license plate directly on the map based upon the respective ...

Подробнее
Номер записи: 58
04-02-2016 дата публикации

IMAGE PROCESSING APPARATUS, IMAGE PROCESSING METHOD, MOVING IMAGE PUBLISHING SYSTEM, MOVING IMAGE PUBLISHING METHOD, AND RECORDING MEDIUM

Номер: US20160034763A1
Автор: TAKANAKA Hidetoshi, YAMAJI Kei
Принадлежит:

A plurality of frame images are extracted from a moving image, and image analysis is performed to determine a scene of each frame image. The plurality of frame images are divided into divided frame image groups according to a replay order of the moving image while taking one frame image different from the scenes of preceding and following frame images in the replay order of the moving image, or two or more frame images, in which the same scene is consecutive, as a divided frame image group. It is determined whether or not to publish each divided frame image group based on the priority of publishing, and frame images included in the divided frame image group determined to be published are combined to generate the digest moving image of the moving image. The digest moving image is uploaded to a server through a network. 1. An image processing apparatus comprising:a frame image extraction unit which extracts a plurality of frame images from a moving image;an image analysis unit which performs image analysis of each frame image to determine a scene of each frame image;a frame image division unit which divides the plurality of frame images into one or more divided frame image groups according to a replay order of the moving image while taking one frame image different from the scenes of preceding and following frame images in the replay order of the moving image, or two or more frame images, in which the same scene is consecutive, as a divided frame image group based on the scene of each frame image;a publishing/non-publishing determination unit which determines whether or not to publish each divided frame image group based on the priority of publishing for a scene of the divided frame image group; anda digest moving image generation unit which combines a part or all of frame images included in the divided frame image group determined to be published to generate a digest moving image of the moving image.2. The image processing apparatus according to claim 1 , further ...

Подробнее
Номер записи: 59
01-02-2018 дата публикации

ELECTRONIC DEVICE AND OPERATION METHOD THEREOF

Номер: US20180033463A1
Автор: Cho Sung Dae, JUNG Yumin, KIM Daehee, LEE Bado, LEE Seoyoung, PARK Ji-Yoon, Shin Dae-Kyu
Принадлежит:

The present disclosure relates to an electronic device and a method of operation thereof, and the electronic device includes: a display; and a processor electrically connected with the display, and the processor is configured to extract a plurality of frames from video data, to identify a size of an object included in each of the extracted frames and a number of objects, to determine a layout regarding each of the extracted frames based on the size of the object and the number of objects, and to display the extracted frames on the display to correspond to the layout. 1. An electronic device comprising:a display; anda processor electrically connected with the display, the processor configured to extract a plurality of frames from video data, to identify at least one of: a size of an object included in each of the extracted frames and a number of objects included in each of the extracted frames, to determine a layout regarding each of the extracted frames based on the size of the object and/or the number of objects, and to display the extracted frames on the display to correspond to the layout.2. The electronic device of claim 1 , wherein the layout comprises at least one of: a size of a frame and a display location of a frame.3. The electronic device of claim 1 , wherein the processor is configured to display a frame comprising a number of objects greater than or equal to a reference number of objects according to a first layout claim 1 , and the first layout comprises a layout for highlighting frames to be distinguished from frames of a second layout.4. The electronic device of claim 1 , wherein the processor is configured to display a frame comprising an object having a size greater than or equal to a reference size according to a first layout claim 1 , and the first layout comprises a layout for highlighting frames to be distinguished from frames of a second layout.5. The electronic device of claim 1 , wherein the processor is configured to display a frame ...

Подробнее
Номер записи: 60
17-02-2022 дата публикации

INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING METHOD, AND PROGRAM

Номер: US20220051432A1
Автор: Hattori Hironori, KAMIYA Koji, TSUBAKI SATOSHI, YAMADA Naohide
Принадлежит: Sony Group Corporation

Provided is an information processing device including: an imaging position information calculation unit that calculates a position and an orientation of an imaging device as imaging device position information on the basis of camera data received from the imaging device in association with video data; and an information display control unit that controls a display of the imaging device position information. Provided is an information processing method performed by a processor, the method including: calculating a position and an orientation of an imaging device as imaging device position information on the basis of camera data received from the imaging device in association with video data; and controlling a display of the imaging device position information. 1. An information processing device comprising:an imaging position information calculation unit that calculates a position and an orientation of an imaging device as imaging device position information on a basis of camera data received from the imaging device in association with video data; andan information display control unit that controls a display of the imaging device position information.2. The information processing device according to claim 1 , whereinthe camera data includes information indicating an angle of view and a focus distance of the imaging device,the imaging position information calculation unit further calculates an imaging range of the imaging device as the imaging device position information on a basis of the information indicating the angle of view and the focus distance of the imaging device, andthe information display control unit controls the display of the imaging device position information including the imaging range.3. The information processing device according to claim 2 , whereinthe camera data further includes characteristics of a lens mounted on the imaging device, andthe imaging position information calculation unit calculates the imaging range on a basis of the ...

Подробнее
Номер записи: 61
02-02-2017 дата публикации

SYSTEM AND METHOD FOR RECOGNITION OF ITEMS IN MEDIA DATA AND DELIVERY OF INFORMATION RELATED THERETO

Номер: US20170034550A1
Автор: McDevitt John
Принадлежит:

The system and method disclosed herein relate to the establishment of both the location and identity of individual items in pictures or videos and delivering of related information thereto. Initially, images in video source content are scanned and individual elements in the images are dynamically compared with digital images stored in a database to identify individual items in the image that match the digital images stored in the database. Upon detecting a match, information is accessed in the database that is related to the digital image that matches the identified individual item. The accessed information is then transmitted to a secondary system that is in communication with a display device, such that the accessed information is displayed on the secondary system in coordination with the video source content being displayed on the display device. 1. A system for recognizing individual items in images contained in video source content displayed on a display device and delivering related information , the system comprising:at least one electronic database storing a plurality of digital images and information related to each of the plurality of digital images; (1) scan at least one of the images contained in the video source content and dynamically compare individual elements in the at least one image with the plurality of digital images stored in the at least one electronic database to identify at least one individual item in the at least one image that matches at least one of the plurality of digital images stored in the at least one electronic database, and', '(2) access the information stored in the at least one electronic database that is related to the at least one digital image that matches the identified at least one individual item; and, 'at least one processor communicatively coupled to the at least one electronic database, the at least one processor configured toat least one server configured to transmit the accessed information related to the at least ...

Подробнее
Номер записи: 62
31-01-2019 дата публикации

CAPTURING NATIVE APPLICATION CONTENT RENDERING PERFORMANCE

Номер: US20190034312A1
Автор: Doraisamy Kandakumar, Karunamoorthy Elango, Koloth Anoop Kumar, Vincent Jancy Latha
Принадлежит:

A system, method, and computer program product are provided for determining a duration of time required to render a web page or other content displayed by a native application running on a user device. One embodiment captures screenshots of the application's displayed output on a user device as video frames, and determines when the displayed output image content stabilizes. Another embodiment measures the number of service calls from a mobile client machine and the data requested and/or sent in response to such calls to determine native application performance. In another embodiment, a configuration file updates application executables and runs batch content rendering performance tests. Embodiments timestamp and store test results for subsequent visual depiction, evaluation, and analysis by developer teams and/or users. Performance variations due to changes to a native application or content may be routed to a particular application developer or content designer for possible correction and improvement. 1. A method for automatically capturing user-perceived content rendering performance by a native application on a user device , the method comprising:rendering a first content element in a display device at a start time;repeatedly rendering subsequent content elements and converting the display device content into a succession of video frames;detecting when the display device content stabilizes at a stop time after which a predetermined time span elapses without further content changes; andoutputting performance data comprising a rendering duration comprising the stop time minus the start time,wherein a clock in the user device provides the start time and the stop time,2. The method of claim 1 , wherein the native application enables use of a networked publication and ecommerce system.3. The method of claim 1 , wherein the user device is a mobile device comprising at least one of a smart phone claim 1 , a laptop computer claim 1 , and a tablet.4. The method of claim 1 ...

Подробнее
Номер записи: 63
31-01-2019 дата публикации

SYSTEMS AND METHODS FOR EDITING VIDEOS BASED ON MOTION

Номер: US20190035429A1
Автор: Patry Jean
Принадлежит:

Motion within first video content and second video content may be assessed. A match between the motions assessed within the first video content and the second video content may be determined. The match may including a first set of video frames within the first video content and a second set of video frames within the second video content within which the matching motion is present. A first video portion (including frame(s) of the first set of video frames) of the first video content and a second video portion (include frame(s) of the second set of video frames) of the second video content may be identified based on the match. The first video portion and the second video portion may be concatenated to provide a transition between the first video portion and the second video portion in which continuity of motion may be achieved. 1. A system for editing videos based on motion , the system comprising: access multiple sets of video information defining multiple videos;', 'assess motion within the multiple videos;', 'determine a match between the motion assessed within at least two of the multiple videos, the match including sets of video frames within the at least two of the multiple videos within which the matching motion is present;', 'identify video portions within the at least two of the multiple videos based on the match, individual ones of the video portions including one or more frames of the sets of video frames within which the matching motion is present;', 'concatenate the video portions such that at least two sets of the one or more frames of the sets of video frames are adjacent, the concatenation of the video portions resulting in at least one transition between the video portions in which continuity of motion is achieved., 'one or more physical processors configured by machine-readable instructions to2. The system of claim 1 , wherein the motion assessed within the multiple videos includes capture motion of the multiple videos.3. The system of claim 2 , ...

Подробнее
Номер записи: 64
08-02-2018 дата публикации

ASSOCIATIVE OBJECT TRACKING SYSTEMS AND METHODS

Номер: US20180036590A1
Автор: DeAngelis Douglas J., Evansen Edward G., Reilly Gerard M.
Принадлежит:

Systems and methods track a first object when continuous tracking information for the first object is not available. The systems and methods detect when the tracking information for the first object is not available. A last time of a last determined location of the first object is determined and a second object closest to the last determined location at the last time is determined. The location of the first object is associated with a location of the second object if tracking information for the first object is not available. 1. A method for annotating a delayed feed of a sporting activity with tracking information determined within a tracking apparatus for a plurality of objects , comprising:determining when continuous location tracking information for a primary one of the plurality of objects is not available;when, for a period when the continuous location tracking information for the primary object is not available and based upon a highest probability defined within one or more predetermined scenarios of the sporting activity, speculatively associating the primary object with a first one of two secondary ones of the plurality of objects that are proximate a last location of the primary object;when the continuous location tracking information for the primary object becomes available after the period, receiving an updated location for the primary object and evaluating correctness of the speculative association of the primary object with the first secondary object based upon the updated location, to produce a non-speculative association of the primary object with one of the secondary objects; andoutputting the delayed feed with the tracking information for the first object based upon tracking information of the non-speculatively associated one of the secondary objects during the period when the continuous location tracking information is not available.2. The method of claim 1 , the step of outputting comprising:when the step of evaluating determines that the ...

Подробнее
Номер записи: 65
04-02-2021 дата публикации

System And Method for Identifying Cognate Image Sequences

Номер: US20210034879A1
Автор: Chenillo Samuel, Gilad Oran, SteinField Oren
Принадлежит:

A system and method of identifying cognate image sequences is disclosed that examines significant frames of a stream of video images using an array of image indexes. The image index array includes image indexes obtained by at least two different image indexing methods. These are compared to a corresponding array of image indices of significant frames of known image sequences. An image quality indicator is used to determine which set of image index thresholds to use in making the comparison. These thresholds are more stringent for higher quality frames. Two image sequences are considered cognate when a string of sufficiently many sequential frame matches is established. In an alternate embodiment, image blurriness is also, or instead, used to determine the appropriate set of image index thresholds. The sets of image index thresholds are determined using machine learning on a curated set of representative images. 1: A method of identifying a cognate image sequence , comprising:providing a database of known video image sequences; obtaining an array of image indexes of said significant frames;', 'determining an image quality indicator of one or more of said significant frames;', 'selecting, based on said image quality indicator, a set of predetermined image index thresholds from an array of predetermined image index thresholds;', for a known video image sequences in which a match has occurred, repeating the preceding steps of comparing using a next significant frame; and,', 'when said matching occurs sequentially for a predetermined number of significant frames in a particular known video image sequence, identifying said incoming stream of video images as being cognate with said particular known video image sequence., 'determining a first significant frame match to have occurred if a difference in the image indices of all the image indices is less than or equal to said selected, predetermined image index threshold corresponding to said image indexing method; and, then ...

Подробнее
Номер записи: 66
04-02-2021 дата публикации

Systems and methods for selecting images

Номер: US20210035281A1
Автор: Benjamin Carpentier, Eva Coupeté, Marc Lebrun
Принадлежит: GoPro Inc

A video may include multiple video frames. The video frames may be scored based on values of multiple content metrics for individual frames. One or more portions of the video that includes a threshold number of consecutive video frames that meet a score threshold may be identified. For individual ones of the identified portion(s), a video frame may be selected based on a maximum of the score for presentation as an exemplar image.

Подробнее
Номер записи: 67
11-02-2016 дата публикации

SENTIMENT ANALYSIS IN A VIDEO CONFERENCE

Номер: US20160042226A1
Автор: CUNICO Hernan A., Silva Asima
Принадлежит:

In an approach to determine a sentiment of an attendee of a video conference, the computer receives a video of an attendee of a video conference and, then, determines, based, at least in part, on the video of the attendee, a first sentiment of the attendee. Furthermore, in the approach the computer receives an indication of an attendee activity on a first application and determines, based, in part, on the attendee activity whether the first sentiment of the attendee is related to the video conference. 1. A method for determining a sentiment of an attendee of a video conference , the method comprising:receiving, by one or more computing devices, a video of an attendee of a video conference;determining, by one or more computing devices, based, at least in part, on the video of the attendee, a first sentiment of the attendee;receiving, by one or more computing devices, an indication of an attendee activity on a first application; anddetermining, by one or more computing devices, based, in part, on the attendee activity whether the first sentiment of the attendee is related to the video conference.2. The method of claim 1 , wherein the indication of attendee activity includes receiving claim 1 , by one or more computing devices claim 1 , one or more of: data including activity within at least the first application and at least one input to a user interface during the video conference.3. The method of further comprising claim 1 , displaying claim 1 , by one or more computing devices claim 1 , the first sentiment of the attendee in the video conference.4. The method of wherein claim 3 , displaying claim 3 , by one or more computing devices claim 3 , includes at least one or more of displaying to a moderator and displaying to one or more additional video conference attendees.5. The method of claim 1 , wherein determining claim 1 , by one or more computing devices claim 1 , based claim 1 , at least in part claim 1 , on the video of the attendee claim 1 , the first sentiment ...

Подробнее
Номер записи: 68
09-02-2017 дата публикации

Image processing device, information storage device, and image processing method

Номер: US20170039709A1
Автор: Yoichi Yaguchi
Принадлежит: Olympus Corp

An image sequence acquisition section acquires an image sequence including a plurality of images. A processing section performs an image summarization process that acquires a summary image sequence based on first and second deletion determination processes that delete some of the images included in the acquired image sequence. The processing section sets an attention image sequence including one at least one attention image included in the plurality of images, selects a first reference image from the attention image sequence, selects a first determination target image from the plurality of images, and performs the first deletion determination process that determines whether the first determination target image can be deleted based on first deformation information that represents deformation between the first reference image and the first determination target image. The processing section sets a partial image sequence from the image sequence, a plurality of images that have been determined to be allowed to remain by the first deletion determination process being consecutively arranged in the partial image sequence. The processing section selects a second reference image and a second determination target image from the partial image sequence, and performs the second deletion determination process that determines whether the second determination target image can be deleted based on second deformation information that represents deformation between the second reference image and the second determination target image.

Подробнее
Номер записи: 69
08-02-2018 дата публикации

PLAY SEGMENT EXTRACTION METHOD AND PLAY SEGMENT EXTRACTION DEVICE

Номер: US20180039825A1
Автор: FUJIKAKE Naomi, Kawaguchi Kyoko
Принадлежит: Panasonic Intellectual Property Management Co., Ltd.

A play segment extraction method or a play segment extraction device extracts a play segment of sports recorded in a sports video using a processor. The processor identifies a referee in a sports video, estimates a posture of the identified referee, estimates an operation of the referee from the estimated posture, and extracts a play segment, based on the estimated operation of the referee. Thereby, it is possible to accurately extract the play segment. 1. A play segment extraction method of extracting a play segment of sports recorded in a sports video using a processor , wherein the processor identifies a referee in the sports video , estimates a posture of the identified referee , estimates an operation of the referee from the estimated posture , and extracts a play segment , based on the estimated operation of the referee.2. The play segment extraction method of claim 1 , wherein the processor estimates the operation of the referee claim 1 , based on transition of the estimated posture.3. The play segment extraction method of claim 1 ,wherein the play segment has multiple attributes, andwherein the processor extracts a play segment from the estimated operation of the referee, based on the attributes of the play segment.4. The play segment extraction method of claim 3 , wherein the play segment includes at least one attribute claim 3 , among a segment from game start to game end of the sports claim 3 , a segment where time is counted in the sports claim 3 , and a segment where switching of sections configuring the sports is used as a unit.5. The play segment extraction method of claim 1 , wherein the processor estimates an angle of an arm of the referee claim 1 , and estimates an operation of the referee claim 1 , based on the estimated angle of the arm.6. The play segment extraction method of claim 1 , wherein the processor determines whether or not the extracted play segment exceeds an allowable period defined by a predetermined length.7. The play segment ...

Подробнее
Номер записи: 70
08-02-2018 дата публикации

DEVICE AND METHOD FOR AUTOMATIC MONITORING AND AUTONOMIC RESPONSE

Номер: US20180039837A1
Автор: SONG Chenfeng
Принадлежит:

The present invention discloses a device and method for automatic monitoring and autonomic response. The device comprises: a video capture unit, used for capturing and transmitting video in real time; an audio capture unit, used for capturing and transmitting audio in real time; a processing device, used for responding to received video and audio; a processing device, used for responding to the received video and audio, recognizing contents of the video and audio, and issuing instruction; and, a responder, used for receiving the instruction and responding according to the instruction. Compared with the prior art, the present invention allows a camera monitoring system to process automatically and respond autonomically when a certain scenario is monitored, while obviating the need for human intervention. 1. An automatic monitoring and autonomous reaction device , comprising:a video capturing unit for collecting and transmitting video in real time;an audio capturing unit for collecting and transmitting audio in real time;a processing device for recognizing the content of the video and audio and issuing an instruction in response to the received video and audio; anda responder for receiving said instruction and responding to said instruction.2. The automatic monitoring and autonomous reaction device of claim 1 , wherein the responder comprises one or more of the following:an actuator for generating a specific reaction in response to the instruction being information requiring a specific reaction;a speaker for issuing a specific response sound in response to the instruction being information requesting a specific response sound; anda display for displaying a specific reaction picture in response to the instruction being information indicating that a specific reaction screen is required to be displayed.3. The automatic monitoring and autonomous reaction device of claim 2 , wherein:the processing device is coupled or comprises a storage for storing monitoring and response ...

Подробнее
Номер записи: 71
09-02-2017 дата публикации

AUTOMATIC IDENTIFICATION AND MAPPING OF CONSUMER ELECTRONIC DEVICES TO PORTS ON AN HDMI SWITCH

Номер: US20170041554A1
Автор: Aggarwal Ashish, Gopinath Vinod, Kumar Siddharth, Mittal Neha, Niclavose Bitto, Satheesh Sharath Hariharpur
Принадлежит:

Methods, systems, and apparatuses are described for automatic identification and mapping of consumer electronic devices to ports on an HDMI switch. A device that is connected to an HDMI switch is identified based on data received over an HDMI connection, and ports on the HDMI switch are automatically mapped and configured. Methods, systems, and apparatuses are described for back-end database creation for automatic identification and mapping of consumer electronic devices to ports on an HDMI switch. The back-end database may be created by the based on video and audio signatures received from a consumer electronic device and based on remote control information and signatures. 1. A method for generating a database of signatures for automatic identification and mapping of an electronic device to a port on a high-definition media interface (HDMI) switch , the method comprising:generating at least one signature of the electronic device;determining an identification of the electronic device as an HDMI source or an HDMI sink; andassociating at least the signature and the identification with an electronic device name or identifier that corresponds to the electronic device in the database.2. The method of claim 1 , wherein the at least one signature comprises a video signature claim 1 , andwherein generating the at least one signature comprises generating the video signature to include a digital video fingerprint.3. The method of claim 2 , further comprising: capturing a logo displayed on a display that identifies the electronic device during a boot up of the electronic device,', 'capturing a logo displayed on a display that identifies the electronic device during normal operation of the electronic device,', 'capturing a template of pixels displayed on a display, or', 'capturing one or more of text, images, blocks of text, and blocks of images displayed on a display that identifies the electronic device., 'generating the digital video fingerprint by performing at least one ...

Подробнее
Номер записи: 72
24-02-2022 дата публикации

EVENT/OBJECT-OF-INTEREST CENTRIC TIMELAPSE VIDEO GENERATION ON CAMERA DEVICE WITH THE ASSISTANCE OF NEURAL NETWORK INPUT

Номер: US20220059132A1
Автор: Sun Luyi, Tang Jian, Xu Ruian
Принадлежит:

An apparatus including an interface and a processor. The interface may be configured to receive pixel data generated by a capture device. The processor may be configured to generate video frames in response to the pixel data, perform computer vision operations on the video frames to detect objects, perform a classification of the objects detected based on characteristics of the objects, determine whether the classification of the objects corresponds to a user-defined event and generate encoded video frames from the video frames. The encoded video frames may be communicated to a cloud storage service. The encoded video frames may comprise a first sample of the video frames selected at a first rate when the user-defined event is not detected and a second sample of the video frames selected at a second rate while the user-defined event is detected. The second rate may be greater than the first rate. 1. An apparatus comprising:an interface configured to receive pixel data generated by a capture device; anda processor configured to (i) receive said pixel data from said interface, (ii) generate video frames in response to said pixel data, (iii) perform computer vision operations on said video frames to detect objects, (iv) perform a classification of said objects detected based on characteristics of said objects, (v) determine whether said classification of said objects corresponds to a user-defined event and (vi) generate encoded video frames from said video frames, wherein (a) said encoded video frames are communicated to a cloud storage service, (b) said encoded video frames comprise (i) a first sample of said video frames selected at a first rate when said user-defined event is not detected and (ii) a second sample of said video frames selected at a second rate while said user-defined event is detected and (c) said second rate is greater than said first rate.2. The apparatus according to claim 1 , wherein said second rate is the same as a frame rate of said video ...

Подробнее
Номер записи: 73
07-02-2019 дата публикации

PERFORMING MULTIPLE QUERIES WITHIN A ROBUST VIDEO SEARCH AND RETRIEVAL MECHANISM

Номер: US20190042584A1
Автор: Fang Hui, Finn Alan Matthew, Jia Zhen
Принадлежит:

The disclosed herein relates to a method, a system, and a computer program product. The method, the system, and the computer program product can include selecting a video segment within a video and extracting a feature set from the video segment. The method, the system, and the computer program product can further include retrieving data information that matches the feature set from a database; determining a degree of similarity between each instance of the data information and the feature set; and presenting a ranked result set based on the degree of similarity. 1. A method , executed by a processor coupled to a memory , comprising:selecting a video segment within a video;extracting a feature set from the video segment;retrieving data information that matches the feature set from a database;determining a degree of similarity between each instance of the data information and the feature set; andpresenting a ranked result set based on the degree of similarity.2. The method of claim 1 , wherein the selecting the video segment within the video comprises receiving an input through a user interface that provides a bounding geometric shape around an object of interest.3. The method of claim 1 , wherein the video comprises a video file in a database or a video stream from a source.4. The method of claim 1 , wherein the feature set comprises a numeric encoding of the video segment.5. The method of claim 1 , further comprising:tracking the video segment by identifying target segments in consecutive frames of the video and extracting feature sets corresponding to each target segment.6. The method of claim 1 , wherein the extracting of the feature set from the video segment utilizes a circular encoding mechanism.7. The method of claim 1 , wherein the ranked result set is presented in a most relevant to a least relevant order according to the degree of similarity.8. A computer program product claim 1 , the computer program product comprising a computer readable storage medium ...

Подробнее
Номер записи: 74
18-02-2021 дата публикации

METHOD AND APPARATUS FOR ORGANIZING MEDIA CONTENT

Номер: US20210049407A1
Автор: Begeja Lee, Gibbon David Crawford, Gopalan Raghuraman, Liu Zhu, Reibman Amy Ruth, Renger Bernard S., Shahraray Behzad, Zavesky Eric
Принадлежит: AT&T Intellectual Property I, L.P.

A method that incorporates teachings of the subject disclosure may include, for example, determining, by a system comprising a processor, more common features of a plurality of images according to similarity matrices indicating relative similarities between instances of common features occurring within multiple images of the plurality of images, defining, by the system, cluster groups associated with the more common features, where each cluster group comprises cluster images of the plurality of images, and where the more common features are present in each the cluster images, and performing, by the system, quality-based filtering on the cluster images to identify a target cluster image to represent the cluster images for each of the cluster groups. Other embodiments are disclosed. 1. A device , comprising:a processing system including a processor; anda memory that stores executable instructions that, when executed by the processor, facilitate performance of operations, comprising:identifying a plurality of features in a plurality of images;selecting a plurality of common features from the plurality of features in the plurality of images;based on similarity metrics indicating similarity between images of the plurality of images, determining a number of cluster groups to be defined for the plurality of images, to obtain a determined number of cluster groups, wherein the determining the number of cluster groups comprises evaluating each of a plurality of candidate cluster group values according to the similarity metrics;defining a plurality of cluster groups comprising the determined number of cluster groups, wherein each cluster group comprises a plurality of cluster images, wherein each cluster group is associated with a common feature of the plurality of common features selected from the plurality of images, and wherein the plurality of cluster groups is defined according to a user interest that is associated with a portion of the plurality of images;receiving a ...

Подробнее
Номер записи: 75
18-02-2016 дата публикации

SYSTEM AND METHOD FOR PROCESSING IMAGE DATA

Номер: US20160048740A1
Автор: WINTER Alexandre
Принадлежит:

The PLACEMETER PLATFORM APPARATUSES, METHODS AND SYSTEMS (“PM-PLATFORM”) transform sensor data and/or feedback via PM-PLATFORM components into notifications, updates, coupons, promotions, transactions and/or activities notifications, updates, coupons, promotions, transactions and/or activities. In one implementation, the PM-PLATFORM comprises a sensor, a memory, and a processor disposed in communication with the sensor and memory, the memory storing processor-issuable instructions to receive raw environment data at a sensor for at least two discrete points in time, analyze the received raw environment data locally to determine an at least one occupancy metric, store the occupancy metric, receive further raw environment data for a further point in time, process the further raw environment data to determine a further occupancy metric, compare the further occupancy metric to at least one previous occupancy metric, and issue a notification based on the comparison. 1. A computer implemented method for analyzing electronic signal data , the method comprising:a processor receiving raw signal data from at least one sensor in an environment at different points in time;the processor analyzing the raw signal data received at each of the different points in time wherein the raw signal data comprises object trajectories;the processor generating a plurality of metrics derived from the raw signal data for each of the different points in time, wherein the plurality of metrics comprise a time at which an object trajectory crosses a predefined threshold;the processor analyzing the plurality of metrics to determine changes in the environment over time; the changes in the environment over time, wherein the changes comprise changes in occupancy of a venue; changes in wait time to go through a line; changes in foot traffic in the environment; historical information regarding the changes in the environment over time; and', 'predicted future changes in the environment over time., 'the ...

Подробнее
Номер записи: 76
07-02-2019 дата публикации

Generating Output Video from Video Streams

Номер: US20190045119A1
Автор: Emmanuel Thomas, Hans Maarten Stokking, Martin Prins, Omar Aziz Niamut
Принадлежит: Koninklijke KPN NV, Nederlandse Organisatie voor Toegepast Natuurwetenschappelijk Onderzoek TNO

A system and method are provided for generating an output video, such as a video panorama, from a plurality of video streams representing different recordings of a scene. The plurality of video streams may be analyzed to identify at least one part of at least one of the plurality of video streams which is to be used in the output video, thereby identifying a contributing part of a video stream. Orchestration metadata may be generated identifying the contributing part. The orchestration metadata may be provided to a stream source from which the video stream originated to enable the stream source to selectively stream the contributing part of the video stream. Effectively, a selection of the stream's video data may be made to avoid or reduce unnecessary bandwidth usage.

Подробнее
Номер записи: 77
16-02-2017 дата публикации

SEMANTIC REPRESENTATION MODULE OF A MACHINE-LEARNING ENGINE IN A VIDEO ANALYSIS SYSTEM

Номер: US20170046576A1
Автор: COBB Wesley Kenneth, EATON John Eric, FRIEDLANDER David S., GOTTUMUKKAL Rajkiran K., RISINGER Lon W., SAITWAL Kishor Adinath, SEOW Ming-Jung, SOLUM David M., URECH Dennis G., Xu Gang, Yang Tao
Принадлежит:

A machine-learning engine is disclosed that is configured to recognize and learn behaviors, as well as to identify and distinguish between normal and abnormal behavior within a scene, by analyzing movements and/or activities (or absence of such) over time. The machine-learning engine may be configured to evaluate a sequence of primitive events and associated kinematic data generated for an object depicted in a sequence of video frames and a related vector representation. The vector representation is generated from a primitive event symbol stream and a phase space symbol stream, and the streams describe actions of the objects depicted in the sequence of video frames. 1. A system for processing data describing a scene depicted in a sequence of video frames , the system comprising:a processor; anda memory communicatively coupled to the processor, the memory comprising computer-readable instructions that, when executed by the processor, cause the system to:identify one or more objects detected in the scene;receive input data associated with the one or more identified objects;evaluate the received input data to identify one or more primitive events, wherein for a first one of the primitive events, a semantic value is provided describing a behavior engaged in by a first one of the objects depicted in the sequence of video frames and wherein the first one of the primitive events has an assigned primitive event symbol;generate, for the first object, a primitive event symbol stream which includes the primitive event symbol corresponding to the first one of the primitive events identified for the first object; andoutput the primitive event symbol stream.2. The system of claim 1 , further comprising:update, for the first object, the primitive event symbol stream as the first object moves about the scene.3. The system of claim 2 , wherein update the primitive event symbol stream further comprising:identify, for the first object, a second one of the primitive events, wherein the ...

Подробнее
Номер записи: 78
16-02-2017 дата публикации

LIVENESS DETECTION

Номер: US20170046583A1
Автор: Khan Usman Mahmood, LOUGHLIN-MCHUGH Eleanor Simone Frederika, Paraskevas Georgios, Rodriguez Francisco Angel Garcia, Tremoulheac Benjamin Robert
Принадлежит:

A liveness detection system comprises a controller, a video input, a feature recognition module, and a liveness detection module. The controller is configured to control an output device to provide randomized outputs to an entity over an interval of time. The video input is configured to receive a moving image of the entity captured by a camera over the interval of time. The feature recognition module is configured to process the moving image to detect at least one human feature of the entity. The liveness detection module is configured to compare with the randomized outputs a behaviour exhibited by the detected human feature over the interval of time to determine whether the behaviour is an expected reaction to the randomized outputs, thereby determining whether the entity is a living being. 1. A liveness detection system comprising:a controller configured to control an output device to provide randomized outputs to an entity over an interval of time;a video input configured to receive a moving image of the entity captured by a camera over the interval of time;a feature recognition module configured to process the moving image to detect at least one human feature of the entity; anda liveness detection module configured to compare with the randomized outputs a behaviour exhibited by the detected human feature over the interval of time to determine whether the behaviour is an expected reaction to the randomized outputs, thereby determining whether the entity is a living being.2. A liveness detection system according to claim 1 , wherein the human feature that the feature recognition module is configured to detect is an eye of the entity.3. A liveness detection system according to claim 2 , wherein providing the randomized outputs comprises controlling the output device to emit at least one light pulse having a randomized timing within the moving image claim 2 , and the expected reaction is an expected pupillary response to the at least one light pulses.4. A liveness ...

Подробнее
Номер записи: 79
15-02-2018 дата публикации

Salient Video Frame Establishment

Номер: US20180046879A1
Автор: Angara Srinivasa Madhava Phaneen, Dhawan Anmol, Jindal Amol, Maini Varun
Принадлежит: ADOBE SYSTEMS INCORPORATED

Salient video frame establishment is described. In one or more example embodiments, salient frames of a video are established based on multiple photos. An image processing module is capable of analyzing both video frames and photos, both of which may include entities, such as faces or objects. Frames of a video are decoded and analyzed in terms of attributes of the video. Attributes include, for example, scene boundaries, facial expressions, brightness levels, and focus levels. From the video frames, the image processing module determines candidate frames based on the attributes. The image processing module analyzes multiple photos to ascertain multiple relevant entities based on the presence of entities in the multiple photos. Relevancy of an entity can depend, for instance, on a number of occurrences. The image processing module establishes multiple salient frames from the candidate frames based on the multiple relevant entities. Salient frames can be displayed. 1. In a digital medium environment to extract frames from a video based at least partially on entities present in one or more photos , a method implemented by at least one computing device , the method comprising:obtaining, by the at least one computing device, a video including multiple frames;obtaining, by the at least one computing device, multiple photos;ascertaining, by the at least one computing device, multiple relevant entities based on the multiple photos;determining, by the at least one computing device, multiple candidate frames from the multiple frames of the video based on one or more attributes of the video;establishing, by the at least one computing device, multiple salient frames by filtering the multiple candidate frames based on the multiple relevant entities; andcontrolling, by the at least one computing device, presentation of the multiple salient frames via a user interface.2. The method as described in claim 1 , wherein the obtaining multiple photos comprises retrieving the multiple ...

Подробнее
Номер записи: 80
16-02-2017 дата публикации

METHOD AND SYSTEM TO CONDUCT ELECTRONIC COMMERCE THROUGH MOTION PICTURES OR LIFE PERFORMANCE EVENTS

Номер: US20170046772A1
Автор: Hendel Rudolf H., Lin-Hendel Catherine G.
Принадлежит:

Systems and methods for enabling a viewer of a motion art form to select an object of interest from within the motion art form are disclosed. The system includes a computing device configured to: receive at least one selection signal from at least one viewer; synchronize the at least one selection signal with an elapse time of the motion art form; and transmit the at least one selection signal to a destination. 140-. (canceled)41. A system that enables a viewer of a motion art form to obtain goods and services displayed as objects within the motion art form , the system comprising:a storage device onto which the motion art form is stored;a display device on which the motion art form is displayed;a picture scene database that indexes scenes of the motion art form with elapsed time from a beginning of the motion art form;a scene-to-object correlator that correlates objects to scenes of the motion art form, so that for each selectable scene of the motion art form there is listed any objects available for a commerce action that appear in the scene of the motion art form;a selection device that is configured to allow a viewer to produce a scene selection signal at a time when the electronic display is displaying a scene of the motion art form; display, in response to a viewer request, information pertaining to any object available for a commerce action that appears in the scene of the motion art form, and', 'provide a venue for the viewer to conduct a commerce action on a selected object selected by the viewer from among any objects that appear in the scene of the motion art form., 'a selection recording device that records the scene signal as indexed to an elapsed time from a start of the motion art form to the scene; and, a computing device that uses the indexed scenes within the database to identify the scene indicated by the scene selection signal, the computing device being configured to42. The system of wherein the display device and the selection device are both ...

Подробнее
Номер записи: 81
06-02-2020 дата публикации

Computing System with Content-Characteristic-Based Trigger Feature

Номер: US20200045380A1
Автор: Konstantinos Antonios Dimitriou, Wilson Harron
Принадлежит: Gracenote Inc

In one aspect, an example method includes (i) receiving, by a computing system, media content; (ii) generating, by the computing system, a fingerprint of a portion of the received media content; (iii) determining, by the computing system, that the received media content has a predefined characteristic; (iv) responsive to determining that the received media content has the predefined characteristic, transmitting, by the computing system, the generated fingerprint to a content identification server to identify the portion of the received media content; and (v) performing an action based on the identified portion of media content.

Подробнее
Номер записи: 82
03-03-2022 дата публикации

VIDEO ANNOTATION SYSTEM FOR DEEP LEARNING BASED VIDEO ANALYTICS

Номер: US20220067381A1
Автор: Kim Kyu-Han, Lin Qun Yang, WANG Shuai, Xie Jun Qing
Принадлежит:

A video annotation system for deep learning based video analytics and corresponding methods of use and operation are described that significantly improve the efficiency of video data frame labeling and the user experience. The video annotation system described herein may be deployed at a network edge and may support various intelligent annotation functionality including annotation tracking, adaptive video segmentation, and execution of predictive annotation algorithms. In addition, the video annotation system described herein supports team collaboration functionality in connection with large-scale labeling tasks. 1. An edge deployment video annotation system , comprising:an edge processor;a datastore communicatively coupled to the edge processor and configured to store video data; and segment video data into a plurality of sets of frames to be annotated;', 'perform predictive annotation on a first set of frames of the plurality of sets of frames to obtain a second set of predictive annotated frames; and', 'provide an interface through which manual annotation of at least one predictive annotated frame is performed by modifying incorrect annotation information associated with the at least one predictive annotated frame., 'a memory operatively connected to the edge processor, the memory including instructions that when executed cause the edge processor to2. The edge deployment video annotation system of claim 1 , wherein the instructions when executed cause the edge processor to segment the video data at least in part by:calculating a frame difference between a first frame of the video data and a neighboring second frame of the video data;determining, based at least in part on the calculated frame difference, that the second frame is to be excluded from the first set of frames.3. The edge deployment video annotation system of claim 2 , wherein the instructions when executed cause the edge processor to determine that the second frame is to be excluded from the first set ...

Подробнее
Номер записи: 83
03-03-2022 дата публикации

MULTIMODAL GAME VIDEO SUMMARIZATION

Номер: US20220067384A1
Автор: Kaushik Lakshmish, Khorram Soheil, Kumar Saket, Rao Sharath, Sundaram Chockalingam Ravi, Yoo Jaekwon, Zhang Kevin
Принадлежит:

Video and audio from a computer simulation are processed by a machine learning engine to identify candidate segments of the simulation for use in a video summary of the simulation. Text input is then used to reinforce whether a candidate segment should be included in the video summary.

Подробнее
Номер записи: 84
03-03-2022 дата публикации

MULTIMODAL GAME VIDEO SUMMARIZATION WITH METADATA

Номер: US20220067385A1
Автор: Kaushik Lakshmish, Khorram Soheil, Kumar Saket, Rao Sharath, Sundaram Ravi, Yoo Jaekwon, Zhang Kevin
Принадлежит:

Video and audio from a computer simulation are processed by a machine learning engine to identify candidate segments of the simulation for use in a video summary of the simulation. Text input is then used to reinforce whether a candidate segment should be included in the video summary. Metadata can be added to the summary showing game summary information. 1. An apparatus comprising:at least one processor programmed with instructions to:receive audio-video (AV) data;provide a video summary of the AV data that is shorter than the AV data at least in part by:input to a machine learning (ML) engine first modality data;input to the ML engine second modality data;receive the video summary of the AV data from the ML engine responsive to the inputting of the first and second modality data; andpresent in the video data metadata aligned in time with the first and second modality data such that the metadata is perceptible in the video summary.2. The apparatus of claim 1 , wherein the first modality data comprises audio from the AV data and the second modality data comprises computer simulation video from the AV data.3. The apparatus of claim 1 , wherein the metadata represents game event data.4. The apparatus of claim 1 , wherein the metadata represents emotion.5. The apparatus of claim 1 , wherein the metadata represents audio and video features extracted from the AV data.6. The apparatus of claim 1 , wherein the instructions are executable to:highlight portions of video that are subject the metadata.7. The apparatus of claim 1 , wherein the instructions are executable to:present the metadata as text in the video summary.8. The apparatus of claim 1 , wherein the metadata indicates likes for certain portions of the AV data.9. A method comprising:identifying an audio-video (AV) entity;using audio from the AV entity, identifying plural first candidate segments of the AV entity for establishing a summary of the entity;using video from the AV entity, identifying plural second ...

Подробнее
Номер записи: 85
03-03-2022 дата публикации

SYSTEMS AND METHODS FOR MIXING DIFFERENT VIDEOS

Номер: US20220068313A1
Автор: SHAFIR NIR Michal
Принадлежит:

There are provided methods and systems for media processing, comprising: providing at least one media asset source selected from a media asset sources library, the at least one media asset source comprising at least one source video, via a network to a client device; receiving via the network or the client device a media recording comprising a client video recorded by a user of the client device; transcoding the at least one source video and the client video which includes parsing the client video and the source video, respectively, to a plurality of client video frames and a plurality of source video frames based on the matching; segmenting one or more frames of the plurality of source video frames to one or more character frames; detecting one or more face images in one or more frames of the plurality of client video frames and provide face markers; resizing the one or more character frames according to the face markers compositing the resized character frames with the background frames using one or more blending methods to yield a mixed media asset frames; and encoding the mixed media asset frames to yield a mixed media asset video.

Подробнее
Номер записи: 86
03-03-2022 дата публикации

METHOD AND APPARATUS FOR STORING EVIDENCE COLLECTION PROCESS VIDEO SEGMENT

Номер: US20220069978A1
Автор: YANG Xinying
Принадлежит:

A method for storing an evidence collection process video segment includes: obtaining a clip-for-storage request initiated by a user, the clip-for-storage request specifying a to-be-clipped evidence collection process video and clipping range information, and the evidence collection process video being obtained by the evidence collection service device by recording evidence collection processes for at least two web pages; determining whether the evidence collection process video is stored in a blockchain, and clipping a video segment from the evidence collection process video based on the clipping range information in response to determining that the evidence collection process video is stored in the blockchain, the video segment recording an evidence collection process corresponding to any one of the at least two web pages; and committing the video segment to the blockchain for storage. 1. A method for storing an evidence collection process video segment , applied to an evidence collection service device and comprising:obtaining a clip-for-storage request initiated by a user, the clip-for-storage request specifying a to-be-clipped evidence collection process video and clipping range information, and the evidence collection process video being obtained by the evidence collection service device by recording evidence collection processes for at least two web pages;determining whether the evidence collection process video is stored in a blockchain, and clipping a video segment from the evidence collection process video based on the clipping range information in response to determining that the evidence collection process video is stored in the blockchain, the video segment recording an evidence collection process corresponding to any one of the at least two web pages; andcommitting the video segment to the blockchain for storage.2. The method according to claim 1 , wherein the obtaining the clip-for-storage request initiated by the user comprises:receiving the clip-for ...

Подробнее
Номер записи: 87
25-02-2016 дата публикации

Scene and Activity Identification in Video Summary Generation Based on Motion Detected in a Video

Номер: US20160055381A1
Автор: ADSUMILLI Balineedu Chowdary, Lustig Ryan, Newman David A.
Принадлежит:

Video and corresponding metadata is accessed. Events of interest within the video are identified based on the corresponding metadata, and best scenes are identified based on the identified events of interest. In one example, best scenes are identified based on the motion values associated with frames or portions of a frame of a video. Motion values are determined for each frame and portions of the video including frames with the most motion are identified as best scenes. Best scenes may also be identified based on the motion profile of a video. The motion profile of a video is a measure of global or local motion within frames throughout the video. For example, best scenes are identified from portion of the video including steady global motion. A video summary can be generated including one or more of the identified best scenes. 1. A method for identifying scenes in captured video for inclusion in a video summary , the method comprising;accessing a video, the video including a plurality of frames;identifying a motion value associated with each frame of the plurality of frames;identifying a differential motion value associated with each frame of the plurality of frames based on the motion value associated with each of one or more of the frames;determining a score for each frame of the plurality of frames based on the motion value and differential motion value associated with each frame;selecting one or more frames in the video based on the determined scores;identifying, for each selected frame, a corresponding video scene, the video comprising a threshold amount of video occurring before and after the selected frame; andselecting one or more identified video scenes for inclusion in a video summary.2. The method of claim 1 , further comprising:receiving a request for a video summary from the user; andgenerating a video summary including a plurality of selected video scenes.3. The method of claim 2 , wherein generating the video summary comprises concatenating the ...

Подробнее
Номер записи: 88
25-02-2021 дата публикации

System and Method of Contextually Converting a Media File into an Electronic Document

Номер: US20210056165A1
Автор: Bannister Paul
Принадлежит:

A system and method of contextually converting a media file into an electronic document allows the user to generate an interactive transcription from the audio portion of a provided media file, which subsequently connects to the media file such that the user can play the media file from a selected transcribed word. Screenshots from video files may also be appended to the electronic document at transitions in video content and subsequently matched to appropriate transcribed words within the generated document. The system implementing the method includes a user account managed by at least one remote server, wherein the user account is associated with a corresponding personal computing (PC) device. This arrangement enables each user to interact with the at least one remote server using the corresponding PC device. The method follows an overall process in order to generate an electronic document with timestamped transcriptions. 1. A method of contextually converting a media file into an electronic document , the method comprises the steps of:(A) providing a user account managed by at least one remote server, wherein the user account is associated with a corresponding personal computing (PC) device;(B) retrieving a media file for the user account with the remote server, wherein the media file includes an audio portion;(C) parsing the audio portion into a plurality of audible content pieces with the remote server, wherein each audible content piece includes an audio timestamp;(D) transcribing the plurality of audible content pieces into a plurality of textual content pieces with the remote server, wherein each textual content piece is associated with a corresponding audible content piece from the plurality of audible content pieces;(E) generating an electronic document from the plurality of textual content pieces with the remote server;providing a video portion for the media file, wherein the video portion includes a series of visual frames, and wherein each visual frame ...

Подробнее
Номер записи: 89
22-02-2018 дата публикации

REAL-TIME FONT EDGE FOCUS MEASUREMENT FOR OPTICAL CHARACTER RECOGNITION (OCR)

Номер: US20180053046A1
Автор: Barton Scott E.
Принадлежит:

A system and process of generating an improved image for optical character recognition is disclosed comprising dynamically obtaining a video source image comprising one or more characters on a background using a video capture device; detecting edges of at least one of the one or more characters that comprise the video source image; determining a sharpness value for the edges of the at least one of the one or more characters, wherein the sharpness value is related to the ability of the video capture device to distinguish the edges of the characters from the background; and indicating at least when the sharpness value is at a predetermined value or within a predetermined range of values. 1. A method of generating an improved image for optical character recognition , the method comprising:dynamically obtaining a video source image comprising one or more characters on a background using a video capture device;providing the video source image to a processor;detecting, by the processor, edges of at least one of the one or more characters that comprise the video source image;determining, by the processor, a sharpness value for the edges of the at least one of the one or more characters, wherein the sharpness value is related to the ability of the video capture device to distinguish the edges of the characters from the background; andindicating, by the processor, at least when the sharpness value is at a predetermined value or within a predetermined range of values.2. The method of claim 1 , further comprising causing claim 1 , by the processor claim 1 , the video capture device to automatically capture a still image of the video source image when the sharpness value is at the predetermined value or within the predetermined range of values.3. The method of claim 2 , wherein the still image is used for optical character recognition.4. The method of claim 1 , wherein dynamically obtaining the video source image containing characters on a background using the video capture ...

Подробнее
Номер записи: 90
23-02-2017 дата публикации

Intelligent Video Thumbnail Selection and Generation

Номер: US20170053170A1
Автор: Fatourechi Mehrdad, Mendoza Lino Evgueno Coria, Rafati Shahrzad
Принадлежит:

In accordance with one embodiment, an intelligent video thumbnail selection and generation tool may select a relevant and visually stimulating image from a video file and generate a thumbnail including the image. The image may be selected by computing a relevancy metric for an image in the file based on one or more selected relevant features, and comparing that relevancy metric with the metric of at least one other image in the file. In another embodiment, a series of images in a video file may be divided into shots. One of the shots may be selected based on a shot relevancy metric and a key image from the shot may be selected as a thumbnail based on a key image relevancy metric, where the shot relevancy metric and the key image relevancy metrics may be computed based on one or more relevant content features. 1. A method for recommending a thumbnail image representative of a collection of images , the method comprising: a size of a face in the image, wherein the relevancy metric is influenced in a first direction more when the face is large than when the face is small;', 'a number of eyes in the image, wherein the relevancy metric is influenced in the first direction more when the number of eyes is large than when the number of eyes is small;', 'a number of open eyes in the image, wherein the relevancy metric is influenced in the first direction more when the number of open eyes is large than when the number of open eyes is small;', 'an object or face in the image, wherein the relevancy metric is influenced in the first direction more when the object or face is identified as corresponding to a database entry than when the object or face is unidentified; and', 'a number of skin-colored pixels in the image, wherein the relevancy metric is influenced in the first direction more when the number of skin-colored pixels is large than when the number of skin-colored pixels is small;, 'obtaining a relevancy metric for each image of the collection of images, wherein the ...

Подробнее
Номер записи: 91
23-02-2017 дата публикации

OBJECT TRACKING AND ALERTS

Номер: US20170053171A1
Автор: Buehler Christopher J.
Принадлежит:

An integrated surveillance system combining video surveillance and data from other sensor-based security networks is used to identify activities that may require attention. 1. A system for generating alerts based on events in an environment , the system comprising:a plurality of cameras for producing video signals representing at least a portion of a environment;a video-processing module for analyzing the video signals to identify objects within the environment;a data-input module for receiving non-video data from at least one sensor-based monitoring system, the data representing one or more events relating to at least one of the identified objects; andan alert module for generating alerts based on at least one of the events.2. The system of wherein the at least one sensor-based monitoring system is a point-of-sale system.3. The system of wherein the at least one sensor-based monitoring system is a electronic article surveillance system.4. The system of further comprising a data storage module for storing rules relating to at least one activity within the environment on which the alerts are based.5. The system of wherein the at least one activity comprises one or more of the identified objects claim 4 , the events in the environment claim 4 , the absence of identified objects claim 4 , and the absence of events.6. The system of further comprising a communications module for transmitting the generated alerts to a remote device.7. The system of wherein the remote device is a hand-held wireless receiver.8. The system of further including a geographic information service module for rendering visual representations of the environment.9. The system of wherein the visual representations of the environment are transmitted to a remote device.10. The system of further comprising annotating the visual representations of the environment.11. The system of wherein the annotations comprise one or more of text claim 10 , color claim 10 , a directional indication claim 10 , and a ...

Подробнее
Номер записи: 92
13-02-2020 дата публикации

AUTOMATIC CREATION OF A GROUP SHOT IMAGE FROM A SHORT VIDEO CLIP USING INTELLIGENT SELECT AND MERGE

Номер: US20200051300A1
Автор: Fatima Andaleeb, Shah Abhishek
Принадлежит:

Systems and techniques are disclosed for automatically creating a group shot image by intelligently selecting a best frame of a video clip to use as a base frame and then intelligently merging features of other frames into the base frame. In an embodiment, this involves determining emotional alignment scores and eye scores for the individual frames of the video clip. The emotional alignment scores for the frames are determined by assessing the faces in each of the frames with respect to an emotional characteristic (e.g., happy, sad, neutral, etc.). The eye scores for the frames are determined based on assessing the states of the eyes (e.g., fully open, partially open, closed, etc.) of the faces in individual frames. Comprehensive scores for the individual frames are determined based on the emotional alignment scores and the eye scores, and the frame having the best comprehensive score is selected as the base frame. 1. A method , performed by a computing device , for automatically creating a group shot image based on intelligent merging of features from frames of a video clip , the method comprising:identifying a video clip of frames comprising images of faces of a group of multiple people;identifying a frame of the video clip to use as a base frame for the group shot image;determining face scores for the faces in the base frame based on scoring the faces in the base frame with respect to alignment with an emotional characteristic and eye state;identifying features of faces in the base frame for replacement based on the face scores of the faces in the base frame;identifying replacement features in other frames of the video clip, wherein the replacement features are identified based on proximity of the other frames of the video clip to the base frame and detecting visibility of the replacement features; andmerging the replacement features from the other frames into the base frame to create the group shot image.2. The method of claim 1 , wherein identifying the ...

Подробнее
Номер записи: 93
04-03-2021 дата публикации

SYSTEMS, DEVICES, AND METHODS EMPLOYING THE SAME FOR ENHANCING AUDIENCE ENGAGEMENT IN A COMPETITION OR PERFORMANCE

Номер: US20210060404A1
Автор: Nolan James Scott, Wanke Todd
Принадлежит:

This document presents devices, systems, and their methods of use for content generation, engagement, and distribution by which a user can interact with collected content in a variety of different manners. Generally, a content engagement platform is provided, where the platform may be implemented on one or more computing devices, such as one or more of: a remote server, a desktop computer, a tablet computer, a handheld mobile computing device, for instance, a mobile phone or personal digital assistant, a smart accessory, such as a watch or eyeglasses, and the like. The platform allows a user to annotate and distribute video content. 1. A computing system for evaluating a performance of an activity , the system comprising:a repository storing one or more videos of the activity, each of the one or more videos being tagged with one or more activity-related identifiers; a library builder that presents a search menu associated with the one or more activity-related identifiers, and in response to a search query, accesses the repository, identifies a selection of the one or more videos related to the search query, and generates a structured library containing a representation of the selection of the one or more videos in a library panel of the interactive graphical user interface of the electronic display device, each of the selection of the one or more videos being selectable from the structured library by a selection input received by the interactive graphical user interface;', 'a presentation module that generates one or more interactive presentation panels in the interactive graphical user interface, and retrieves a selected video from the structured library for presentation in one of the one or more interactive presentation panels;', 'a tool module that provides one or more graphical tools in a tool panel in the interactive graphical user interface, each of the graphical tools being configured to receive an input for controlling the presentation of the selected video, ...

Подробнее
Номер записи: 94
10-03-2022 дата публикации

System and Method for Player Reidentification in Broadcast Video

Номер: US20220076054A1
Автор: Cherukumudi Aditya, Ganguly Sujoy, Lucey Patrick Joseph, SHA Long, WEI Xinyu
Принадлежит: STATS LLC

A system and method of re-identifying players in a broadcast video feed are provided herein. A computing system retrieves a broadcast video feed for a sporting event. The broadcast video feed includes a plurality of video frames. The computing system generates a plurality of tracks based on the plurality of video frames. Each track includes a plurality of image patches associated with at least one player. Each image patch of the plurality of image patches is a subset of the corresponding frame of the plurality of video frames. For each track, the computing system generates a gallery of image patches. A jersey number of each player is visible in each image patch of the gallery. The computing system matches, via a convolutional autoencoder, tracks across galleries. The computing system measures, via a neural network, a similarity score for each matched track and associates two tracks based on the measured similarity. 1. A method , comprising:retrieving, by a computing system, a broadcast video feed for a sporting event, the broadcast video feed comprising a plurality of video frames;generating, by the computing system, a plurality of tracks based on the plurality of video frames, wherein each track comprises a plurality of image patches associated with at least one player, each image patch of the plurality of image patches being a subset of a corresponding frame of the plurality of video frames;connecting, by the computing system, gaps between sets of tracks of the plurality of tracks, the connecting comprising generating a motion field that estimates player motion across a set of video frames of the plurality of video frames;constructing, by the computing system, a predicted motion for each player in the broadcast video feed based on the motion field for a respective player; andgenerating, by the computing system, a graphical representation of each player across a respective set of video frames.2. The method of claim 1 , wherein retrieving claim 1 , by the computing ...

Подробнее
Номер записи: 95
21-02-2019 дата публикации

Video Content Summarization and Class Selection

Номер: US20190057258A1
Автор: Das Manav Nath, Simske Steven J, Zhang Tong
Принадлежит:

A system includes a plurality of summarization engines, each summarization engine to receive video content, via a processing system, and to provide a summary of the video content, thereby providing a plurality of summaries of the video content. The system includes a plurality of meta-algorithmic patterns, each meta-algorithmic pattern to be applied to at least two of the summaries to provide, via the processing system, a meta-summary of the video content using the at least two summaries, thereby providing a plurality of meta-summaries of the video content. The system includes an evaluator to evaluate the plurality of summaries and the plurality of meta-summaries and to determine similarity measures of the video content over each given class of a plurality of classes of video content, and to select a class of the plurality of classes based on the determined similarity measures. 1. A system comprising:a plurality of summarization engines, each summarization engine to receive video content, via a processing system, and to provide a summary of the video content, thereby providing a plurality of summaries of the video content;a plurality of meta-algorithmic patterns, each meta-algorithmic pattern to be applied to at least two of the summaries to provide, via the processing system, a meta-summary of the video content using the at least two summaries, thereby providing a plurality of meta-summaries of the video content; andan evaluator to evaluate the plurality of summaries and the plurality of meta-summaries and to determine similarity measures of the video content over each given class of a plurality of classes of video content, and to select a class of the plurality of classes based on the determined similarity measures.2. The system of claim 1 , wherein at least one of the summarization engines outputs image features claim 1 , audio features claim 1 , and textual features from speech recognition claim 1 , based on the video content.3. The system of claim 1 , wherein at ...

Подробнее
Номер записи: 96
01-03-2018 дата публикации

Dynamic 3d object recognition and printing

Номер: US20180059631A1
Автор: Nicholas Newell, Swapnil Tilaye
Принадлежит: ECHOSTAR TECHNOLOGIES LLC

Three-dimensional (3D) object manufacturing systems and methods are operable to manufacture printed 3D objects corresponding to user-selected physical objects of interest shown in a media content event that have been viewed by a user, wherein at least one 3D printer that is accessible by the user of the media device is operable to manufacture the printed 3D object corresponding to the viewed physical object of interest.

Подробнее
Номер записи: 97
03-03-2016 дата публикации

SEARCHING AND RANKING OF CODE IN VIDEOS

Номер: US20160063102A1
Автор: Yahav Eran
Принадлежит: Codota Dot Com Ltd.

A method comprising: receiving a multiplicity of videos from a source; for each video: receiving meta data related to the video; extracting from the video a video frame containing computer code; identifying a region of interest (ROI) within the video frame; performing OCR of the ROI to extract a code segment; analyzing the code segment by: semantically analyzing the code segment to obtain a first rank, structurally analyzing the code segment to obtain a second rank, and analyzing the meta data to obtain a third rank; and combining the first rank, second rank and third rank into a total rank associated with the code segment; receiving a query; matching the query to each code segment to identify matching code segments and associated videos; and providing the associated videos in accordance with total ranks associated with the matching code segments. 1. A method for providing a video in response to a query , the method comprising using at least one hardware processor for:receiving a multiplicity of videos from a source; receiving meta data related to the video;', 'extracting from the video a video frame containing computer code;', 'identifying a region of interest (ROI) within the video frame;', 'performing optical character recognition (OCR) of the ROI to extract a code segment;', (a) semantically analyzing the code segment to obtain a first rank,', '(b) structurally analyzing the code segment to obtain a second rank, and', '(c) analyzing the meta data to obtain a third rank; and, 'analyzing the code segment, said analyzing comprising, 'combining the first rank, second rank and third rank into a total rank associated with the code segment;, 'for each videoreceiving a query;matching the query to each code segment to identify matching code segments and associated videos; andproviding the associated videos in accordance with total ranks associated with the matching code segments.2. The method according to claim 1 , further comprising displaying to a user a list of videos ...

Подробнее
Номер записи: 98
01-03-2018 дата публикации

Methods and systems enabling access by portable wireless handheld devices to data associated with programming rendering on flat panel displays

Номер: US20180060668A1
Автор: Luis M. Ortiz, Luis Miguel Ortiz
Принадлежит: Individual

Flat panel displays can broadcast their identity for discovery by handheld devices interested in obtaining data associated wit, video programming displayed on the displays. An application can be downloaded and activated on smartphones that will enable them to capture an image of the video programming and recognize is with the help of a remote server, or wirelessly obtain a list of available (discovered) flat panel displays (multiple screens, depending on venue) that allow wireless access to data associated with video programming displayed (or previously displayed and stored in a queue) on flat panels. Video programming rendering on a flat panel of interest can be identified via the smartphone and the smartphone can access additional data either directly from the flat panel or from a remote server once the data has been identified and/or engage in an interactive session in association with the displayed programming or data.

Подробнее
Номер записи: 99
03-03-2016 дата публикации

VIDEO PREVIEW CREATION WITH AUDIO

Номер: US20160064034A1
Автор: McIntosh David, Pennello Chris
Принадлежит:

Providing a method for creating and displaying portions of videos called video previews. The video previews may be associated with audio, such that when the video previews are activated, the audio may play with the video preview. When multiple video previews are organized to play as a playable group or composite of video previews, a corresponding composite audio file can play in response to an activation of the composite. 1. A method comprising:receiving, by a computing device, a composite audio-video object, wherein the composite audio-video object includes a first video preview, a second video preview, wherein a composite audio file is associated with the composite audio-video object and the composite audio file is played according to a composite audio rule when the composite of video previews is activated;identifying, by the computing device, that the composite audio-video object is activated; andin response to the activation of the composite audio-video object, simultaneously playing the first video preview, the second video preview, and the composite audio file according to the composite audio rule.2. The method of claim 1 , wherein the composite audio file is looped to play continuously while the first video preview and the second video are played.3. The method of claim 1 , wherein the composite audio file is looped to play continuously according to a composite audio rule.4. The method of claim 1 , wherein the composite audio file is looped to play continuously while the composite audio-video object is active.5. The method of claim 1 , wherein the composite audio file is not played for at least a portion of the time that the first video preview is playing.6. The method of claim 1 , wherein the duration of the composite audio file is shorter than the duration of the first video preview.7. A computer product comprising a non-transitory computer readable medium storing a plurality of instructions that when executed control a computer system to play a video ...

Подробнее
Номер записи: 100