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.
11-07-2023 дата публикации

Water supply device of steel plate ultrasonic phased array detection equipment

Номер: CN116411609A
Автор: FENG XUE, WANG CHAO, WANG CHUXIA, DU YUPING, LIU FENYONG, LIN ZHIRUI, SANG XIAOHAI, MA JUN, XIAO WEI, MA YONG, WANG YONGTING, YANG DERONG
Принадлежит:

The invention discloses a water supply device of steel plate ultrasonic phased array detection equipment, and relates to the technical field of steel plate nondestructive detection. The water inlet end of the filtering water tank is communicated with the water outlet end of the bag type filter; the water supply pump group comprises a first water supply pump, a second water supply pump and a third water supply pump, the water inlet ends of the water supply pumps are communicated with the water outlet end of the filtering water tank, the water outlet ends of the water supply pumps are connected with water supply pipelines, and the three water supply pipelines are respectively communicated with the water inlet end of the ultrasonic phased array detection equipment; and the water return end of the ultrasonic phased array detection equipment is communicated with the water inlet end of the bag filter through a return pipeline. Impurities in circulating water are effectively removed through the ...

Подробнее
Номер записи: 1
21-07-2023 дата публикации

Infrared visible image fusion method based on self-supervised feature decoupling

Номер: CN116468644A
Автор: TAN JUN, ZHAO YUN, ZHANG HONGQING, SHI GANG, LI PEIYUN, WEN HUBIAO, XU LIQIONG, ZHANG XINGGUO, LIN ZHIRUI, WANG YUANMIN
Принадлежит:

The invention relates to the technical field of computer vision, in particular to an infrared visible image fusion method based on self-supervised feature decoupling. Comprising the following steps: constructing an infrared visible image coding and decoding fusion network based on illumination perception; designing a feature decoupling twin network pre-training method based on comparative learning; designing a cross attention feature supplementing module; and designing a feature fusion method based on channel attention. According to the design, the difference characteristics of double sources can be enhanced through a comparative learning method; a feature supplementing module based on cross attention is added to enhance feature information of each channel, and information exchange among different source features is achieved; the infrared image texture feature, the visible light image texture feature and the visible light image color feature of the fused image are enhanced, so that the ...

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

Model training method and device, object loss prediction method and device and electronic equipment

Номер: CN116070715A
Автор: LIN ZHIRUI, HE YICHAO, ZHU FURONG, LI JINGDAN, LI BOZUN
Принадлежит:

The invention provides a model training method and device, an object loss prediction method and device and electronic equipment, and relates to the technical field of artificial intelligence and big data, and the method comprises the steps: constructing a positive sample pair according to the object information of objects of the same type, constructing a negative sample pair according to the object information of objects of different types, the object information comprises behavior information, attribute information and activeness information, and the recognition model can learn semantic information among similar object information and semantic information among dissimilar object information according to each piece of object information contained in the positive sample pair and each piece of object information contained in the negative sample pair; therefore, when the identification model obtained by training identifies the object information of the same type of objects, the difference ...

Подробнее
Номер записи: 3