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 3. Отображено 3.
27-06-2023 дата публикации

Appearance-based human eye three-dimensional line-of-sight direction estimation method, system and device

Номер: CN116343290A
Автор: LI LIN, WU XINMEI, LI LINFENG, ZHU HAIHONG, WANG YANGGANG, YANG MINGJIE, YAN RUYU
Принадлежит:

The invention discloses an appearance-based human eye three-dimensional sight line direction estimation method, system and device. The method comprises the following steps: acquiring an image or video containing a human face; performing face detection in an image or video frame, and introducing a face key point detection algorithm to realize detection and positioning of face key points; respectively cutting a face image and left and right eye images according to the face detection result and the positions of the key points; a sight line estimation model is used for estimating the three-dimensional sight line of human eyes in the image, and the training process of the sight line estimation model comprises the following steps: carrying out feature extraction on the face image by using a Base-CNNs network to obtain a full face image feature vector; the two asymmetric branch structures of the EE-Net network are used to carry out finer-grained feature extraction on the left eye image and the ...

Подробнее
Номер записи: 1
04-07-2023 дата публикации

Human eye sight drop point estimation method and system, and electronic equipment

Номер: CN116386103A
Автор: LI LIN, WU XINMEI, ZHU HAIHONG, LI SIYU, YU LU, YAN RUYU
Принадлежит:

The invention discloses a human eye sight drop point estimation method and system and electronic equipment. The method comprises the following steps: acquiring an image or video containing a human face; detecting a face in the collected video or image by using a face detection algorithm, and positioning face key points by using a key point detection algorithm; according to the positions of the key points and a face detection result, left and right eye images and a face image; and inputting the images and a face grid image capable of representing the relative position of the human face in the images into a human eye sight line drop point estimation model for estimating the final human eye sight line drop point. The human eye sight drop point estimation model comprises a Base-CNNs network and an EE-Net network, the Base-CNNs network extracts full face image features containing less detail information, and the EE-Net network containing two asymmetric branches performs finer-grained feature ...

Подробнее
Номер записи: 2
05-05-2023 дата публикации

Workpiece defect detection method based on deep neural network

Номер: CN116071327A
Автор: ZHU HAIHONG, LI SIYU, LI LIN, YU LU, LI LINFENG, HU LUNTING, WU XINMEI
Принадлежит:

The invention provides a workpiece defect detection method based on a deep neural network. Image enhancement processing is performed on the training image according to the global features of the image, so that the problem of inconsistent image quality caused by different environment illumination is alleviated, and the environment adaptability of a defect detection algorithm is enhanced; a deep neural network is used as a backbone network for feature extraction, and deeper semantic information is obtained; according to the method, feature fusion of shallow-layer features and deep-layer information is carried out in a feature pyramid, context information is fully utilized, and an attention mechanism is introduced, so that interference of fused features on original detail features is inhibited, effective fusion of semantic information and detail information is realized, and the detection performance of defects of various scales is improved. According to the invention, defects of various types ...

Подробнее
Номер записи: 3