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 5. Отображено 5.
23-06-2023 дата публикации

Low-illumination image defogging method based on lightweight deep neural network

Номер: CN116309110A
Автор: ZHU WEI, CHEN PING, TAN QINGQING, JI XIANYANG, DONG XIAOSHU, WU LIANGHAO, SUN YIBIN, XIN FUHAO, ZHANG LIN
Принадлежит:

The invention discloses a low-illumination image defogging method based on a lightweight deep neural network, and mainly solves the problems that in a low-illumination scene, foggy image feature extraction is difficult, effective correction of image color cast is lacked, and a defogging network is complex in structure and occupies more resources. The method comprises the following steps: constructing a training and testing data set containing a synthetic low-illumination fog image and a real low-illumination fog image; constructing an end-to-end lightweight deep neural network for low-illumination image defogging, wherein the end-to-end lightweight deep neural network comprises a lightweight multistage feature fusion sub-module and a lightweight channel attention sub-module; constructing a network target loss function; training the network by using the constructed data set; and inputting a foggy image in a low-illumination scene into the trained network to obtain a defogged image. On the ...

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

Sea clutter suppression processing and performance analysis method based on video signals

Номер: CN115902807A
Автор: ZHAO YULI, ZHAI HAITAO, LI XUN, WANG ZEZHONG, ZHAO MINYAN, XU YONG, SHANG KAI, ZHAO PENGPENG, CHEN SHUO, LIU WEN, DONG XIAOSHU, TANG SHIYAO, MO BAOHUA
Принадлежит:

The invention provides a sea clutter suppression processing and performance analysis method based on a video signal, and the method comprises the steps: carrying out the high-false-alarm high-detection-probability detection of a preprocessed radar echo, carrying out the inter-frame correlation detection, SIC inter-frame accumulation detection, and traditional CFAR detection multi-channel detection, and carrying out the detection of a high false alarm rate and a high detection probability. And finally, according to the sea clutter region information, carrying out combinational logic judgment on the multi-channel detection result. According to the processing flow, sea clutters can be effectively suppressed through inter-frame accumulation, improvement of the detection performance of inter-frame static or slow targets is facilitated, and the detection performance of moving targets is ensured through multi-channel detection.

Подробнее
Номер записи: 2
04-04-2023 дата публикации

Image translation method based on comparative learning

Номер: CN115909002A
Автор: XING ZHIQIANG, DONG XIAOSHU, GUO BO, XIN FUHAO, YU SIYAO, ZHANG DIAN, WANG YANGHONG, WU HUAN
Принадлежит:

The invention discloses an image translation method based on comparative learning. The method comprises the following steps: inputting an input image into a generator; inputting the image generated by the generator and the real image of the target domain into a discriminator; calculating the loss of the generative adversarial network; inputting the input image and the output image of the generator into an encoder in the generator again, inputting encoding vectors of the input image and the output image into the mapping network to obtain feature vectors of the input image and the output image in the same feature space, and calculating comparison loss between the feature vectors of the input image and the output image; the contrast loss is optimized by using the focus loss; and carrying out back propagation on the generative adversarial network loss and the optimized comparison loss, and optimizing the network. According to the invention, the model generated by using the contrast loss can ...

Подробнее
Номер записи: 3
25-02-2015 дата публикации

Fast image splicing method based on improved SURF algorithm

Номер: CN104376548A
Автор: DONG XIAOSHU, QIN XUAN, BIAN ZHIGUO, LU MINHAO, LIU CHAO, LI LANJUN
Принадлежит:

The invention discloses a fast image splicing method based on an improved SURF algorithm. An existing corner extraction method and an existing corner feature description method are improved, mismatching of extracted corners is eliminated, and multiple images can be spliced fast. At first, an improved FAST algorithm is adopted for increasing the extracted corners, the operation speed of the FAST algorithm for extracting the corners is high, and after the improvement is carried out, the stability is good; secondly, the combination of SURF description and LBP description is adopted for describing the corner feature, and in this way, the speed for matching the corners can also be increased; then an RANSAC method is adopted for eliminating mismatching, accuracy is improved, and a more accurate transformation matrix is obtained, so that fast splicing is carried out; finally, according to obtained matching point pairs, parameters for transforming images to be spliced into reference images are ...

Подробнее
Номер записи: 4
02-06-2023 дата публикации

Airport flight area target real-time detection method based on multi-scale feature decoupling

Номер: CN116206257A
Автор: JI XIANYANG, ZHU WEI, HU DI, DONG XIAOSHU, WANG XIAO, XIN FUHAO, XING ZHIQIANG, QI MEIBIN, ZHUANG SHUO
Принадлежит:

The invention discloses an airport flight area target real-time detection method based on multi-scale feature decoupling, and the method comprises the steps: 1, obtaining an airport flight area monitoring video, and constructing an airport flight area target detection data set; 2, constructing a multi-scale feature fusion module to realize detection of targets of different scales; 3, classifying and positioning tasks in target detection are decoupled, and a learning network based on feature decoupling is constructed; and 4, adding a learning network based on feature decoupling and a multi-scale feature fusion module into a YOLOv5 target detection network, and training and optimizing a target detection model in combination with a loss function. According to the method, shallow detail information and deep semantic information are aggregated by using the multi-scale feature fusion module, the detection capability of targets of different scales is enhanced, classification and positioning tasks ...

Подробнее
Номер записи: 5