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.
02-05-2023 дата публикации

Hyperspectral image classification method based on improved Swinin-Transform network

Номер: CN116051886A
Автор: JING WEIPENG, LI CHAO, KANG PEILUN, CHEN GUANGSHENG, GU JUNTAO
Принадлежит:

The invention discloses a hyperspectral image classification method based on an improved Swin-Transform network, and the method comprises the steps: S1, providing a spatial spectrum recombination module for the characteristics of hyperspectral data, and carrying out the preprocessing of the data; and S2, improving a Swin-Transform network, and adding a cross-layer fusion module in the network to avoid information loss in an interlayer feedforward process. By fusing the output of the current layer and the output of the previous layer in the network, the transmission of information from a shallow layer to a deep layer is realized, so that the loss of effective information in a feedforward process is avoided; and S3, inserting a spatial spectrum recombination module into the improved Swin-Transform network, and taking the disclosed hyperspectral image data as training data. The method has the advantages that the accuracy is higher, the efficiency of mining the spectral information by the network ...

Подробнее
Номер записи: 1
30-05-2023 дата публикации

Method, device and equipment for intelligently detecting defects of aluminum substrate and medium

Номер: CN116188362A
Автор: DI DONGLIN, RU BINXIN, KANG PEILUN, ZHAO CHENXU, JI CONG
Принадлежит:

The invention belongs to the technical field of image processing, and particularly relates to a method, a device, equipment and a medium for intelligently detecting defects of an aluminum substrate, and the method comprises the following steps: acquiring an image of a to-be-detected aluminum substrate; preprocessing the image to obtain a preprocessed image; performing positioning processing on the pre-processed image to obtain a positioning image; cutting the positioning image to obtain a target image; and performing defect detection based on the target image to obtain a detection result of the to-be-detected aluminum substrate. The image of the aluminum substrate to be detected is processed and detected, so that the tiny defects on the surface of the aluminum substrate are detected, and the tiny defects on the surface of the aluminum substrate are accurately detected.

Подробнее
Номер записи: 2
02-05-2023 дата публикации

Patch welding quality inspection method, device and equipment and storage medium

Номер: CN116051485A
Автор: RU BINXIN, DI DONGLIN, KANG PEILUN, ZHAO CHENXU, JI CONG
Принадлежит:

The invention relates to the technical field of computers, and provides a patch welding quality inspection method, device and equipment and a storage medium, and the method comprises the steps: obtaining an image of a PCB welded with a patch; performing patch detection and bonding pad detection on the PCB image by using a pre-trained patch and bonding pad detection model based on deep learning to obtain a detected patch frame and a detected bonding pad frame; calculating a deviation angle of the detected patch frame based on the detected patch frame and the detected bonding pad frame; calculating the offset distance of the patch frame based on the detected offset angle of the patch frame and the detected patch frame; calculating the actual area of an effective welding area based on the detected bonding pad frame; and calculating the proportion of bubbles in the effective welding area based on the effective welding area. The method has better stability and generalization, so that the method ...

Подробнее
Номер записи: 3