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 4. Отображено 4.
29-08-2023 дата публикации

Fine-grained small sample classification method and system for ship remote sensing image

Номер: CN116665149A
Автор: GAO GUI, ZHOU PING, LIU JIA, YAO LIBO, DUAN DINGFENG, LIU TAO, ZHANG XI, GUO FEI
Принадлежит:

The invention provides a fine-grained small sample classification method and system for ship remote sensing images, belongs to the technical field of target recognition, and solves the problems that in the prior art, cost for obtaining a large number of ship images is high, a large number of annotation data is not easy to obtain, and overfitting is very easy if a deep neural network model with a large number of parameters is adopted; therefore, poor classification precision is easily caused. The method comprises the steps of obtaining ship images to form a ship data set; preprocessing each ship image in the ship data set; constructing a feature extraction module and a measurement classification module of the ship target fine-grained small sample, and training the feature extraction module and the measurement classification module based on the ship data set obtained through preprocessing; and based on the trained feature extraction module and the metric classification module, classifying ...

Подробнее
Номер записи: 1
13-06-2023 дата публикации

Combined feature multi-source satellite information track association method and system

Номер: CN116256781A
Автор: YAO LIBO, MENG JIE, SUN WEIWEI, LIN XUN, XIAO HUACHAO, LI XIAOBO, GAO FEI
Принадлежит:

The invention discloses a combined feature multi-source satellite information track association method and system, and relates to the technical field of ship target data association tracking processing, and the method comprises the steps: dividing and selecting a reference remote sensing satellite sensor and one or more auxiliary remote sensing satellite sensors based on track prior information; determining a reference measurement triangle in each measurement moment according to the standby track data corresponding to the reference remote sensing satellite sensor; determining an auxiliary measurement triangle in each measurement moment according to the standby track data corresponding to the auxiliary remote sensing satellite sensor; determining the track measurement similarity; performing coordinate transformation on the to-be-used track data corresponding to the auxiliary remote sensing satellite sensor based on the track measurement similarity to obtain optimized auxiliary measurement ...

Подробнее
Номер записи: 2
30-05-2023 дата публикации

Full-polarization SAR ship detection method capable of sensing scattering characteristics

Номер: CN116189001A
Автор: GAO GUI, ZHANG CHUAN, YU WENXIAN, YAO LIBO, XIA ZHENGHUAN, DUAN DINGFENG, ZHANG XI
Принадлежит:

The invention discloses a scattering characteristic sensing full-polarization SAR ship detection method, which comprises the following steps: S1, performing four-component decomposition on full-polarization SAR data to obtain mirror scattering, double-hop scattering, +/-45-degree dipole and asymmetric scattering components, constructing a feature vector as input data of a ship detection network by using double-hop scattering, +/-45-degree dipoles and asymmetric scattering components; s2, sensing contribution rates of different scattering mechanisms to the target according to a scattering characteristic sensing module constructed according to characteristic differences presented by the target under the different scattering mechanisms; and S3, detecting a target in the fully polarized SAR image by using a scattering characteristic perceived ship detection network. The scattering characteristic sensing module is designed by combining the characteristic difference of the target in different ...

Подробнее
Номер записи: 3
30-05-2023 дата публикации

Ship target motion state estimation method and system based on video satellite

Номер: CN116188519A
Автор: YAO LIBO, LIU YONG, MENG JIE, SUN WEIWEI, XIAO HUACHAO, LI XIAOBO, SHENG LEI, QIAO XINGWANG
Принадлежит:

The invention discloses a ship target motion state estimation method and system based on a video satellite, and relates to the technical field of satellite remote sensing information processing. The method comprises the following steps: acquiring video satellite images of a target area at any two moments to obtain a first image and a second image; respectively and sequentially carrying out image segmentation and rotating rectangular frame fitting operation on the first image and the second image to obtain size parameters of rectangular frames corresponding to the ships in the two images; calculating position parameters of the ships in the two images based on the size parameters of the rectangular frames corresponding to the ships in the two images; performing target association on the ships in the two images according to the position parameters of the ships in the two images to obtain a target association result; and obtaining a ship direction estimation value according to the target association ...

Подробнее
Номер записи: 4