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.
25-07-2023 дата публикации

Single-body planar building detection method based on SegFormer

Номер: CN116486276A
Автор: RUI JIE, LI MEILIN, LIU ZHI, YANG SONGKUN, JIN FEI, WANG SHUXIANG, LIM WOO-JUN, REN LIQIU, CHEN SHUANGJUN
Принадлежит:

The invention provides a single body planar building detection method based on SegFormer. The method comprises the following steps: step 1, constructing a building extraction network based on improved SegFormer, wherein the building extraction network comprises an encoder and a decoder; the encoder comprises four Transform blocks which are connected in sequence from a shallow layer to a deep layer; the decoder comprises a first 1 * 1 convolution layer, an ASPP module and a semantic fusion module which are connected in sequence from a shallow layer to a deep layer; wherein the remote sensing image is input to the first Transform block, the output of the first Transform block is used as one input of the semantic fusion module, the output of the fourth Transform block is used as the input of the first 1 * 1 convolution layer, and the output of the ASPP module is used as the other input of the semantic fusion module; the output of the semantic fusion module is a detection result; step 2, training ...

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

Optical remote sensing image ground object detection method based on YOLOX

Номер: CN116385876A
Автор: RUI JIE, LI MEILIN, LIU ZHI, YANG SONGKUN, JIN FEI, WANG SHUXIANG, LIM WOO-JUN, ZUO XIBING, MA LI, ZHU YAN
Принадлежит:

The invention discloses an optical remote sensing image ground object detection method based on YOLOX, and the method comprises the steps: firstly designing a feature extraction module based on a CBMA mixed domain convolution block attention mechanism, and paying more attention to the feature information of a positive sample in a feature image; secondly, an ASFF module is added to a feature extraction module PANET, so that the problem of multi-scale target detection is solved; and finally, by introducing EIoU loss and VariFocalLoss loss, the real distance error of the two predicted targets is accurately reflected, and the multi-target detection performance is improved. An experiment is carried out on a DOTA data set, and the optimal mechanism and effectiveness of the improved method are verified through an ablation experiment and a contrast experiment. On the premise that an ASFF mechanism and a CBAM attention mechanism are added, the improved network model mAP precision reaches 70.75% ...

Подробнее
Номер записи: 2
19-05-2023 дата публикации

Optimal sorting method for construction of power supply grids of power distribution network based on space-time compass distribution

Номер: CN116136988A
Автор: YE CHEN, REN JIAORONG, WENG GEPING, CHU XUELI, FANG JIANDI, JIANG HAO, WENG BINGYU, CUI QINYUE, LONG ZHENGXIONG, QING HUA, XIE CHU, WANG ZAIPING, JIANG NIAN, YANG SONGKUN, HE PENGFEI
Принадлежит:

The invention discloses a power distribution network power supply grid construction optimization sorting method based on space-time compass distribution, and the method comprises the steps: S1, dividing a planning construction land into a plurality of power supply grids, and classifying the power supply grids into a plurality of first classification sets according to the function bearing characteristics; s2, classifying the first classification set according to the power consumption characteristics to obtain a plurality of second classification sets; s3, performing planning configuration on the second classification set based on the power utilization level; s4, obtaining a first score table according to the external demand degree corresponding to each power supply grid, obtaining a second score table according to the external demand degree, and constructing a joint score table based on the green channel weight; s5, performing construction goodness grading on each power supply grid according ...

Подробнее
Номер записи: 3
28-07-2023 дата публикации

Large-range remote sensing image rural block type residential area extraction method and system fusing target detection and visual attention mechanism

Номер: CN116503750A
Автор: RUI JIE, LI MEILIN, LIU ZHI, YANG SONGKUN, JIN FEI, WANG SHUXIANG, LIM WOO-JUN, ZUO XIBING, HUO AIMEI
Принадлежит:

The invention belongs to the technical field of residential area extraction, and discloses a large-range remote sensing image rural block type residential area extraction method and system fusing target detection and a visual attention mechanism, and the method comprises the steps: generating a residential area candidate area detection frame on a large-range remote sensing image through YOLOv7 model detection; and using a PgNet model to accurately extract the residential areas based on the candidate area detection frame to obtain the rural residential areas on the large-range remote sensing image. According to the method, the candidate mechanism and the visual attention mechanism of the target detection technology are combined, vegetation and terrains are roughly removed, rapid and automatic extraction of rural residential areas and buildings thereof is facilitated, and the retrieval efficiency is improved. After the candidate frames are obtained, a PgNet efficient extraction mechanism ...

Подробнее
Номер записи: 4
23-06-2023 дата публикации

Inland water body extraction method fused with void space pyramid pooling

Номер: CN116310871A
Автор: RUI JIE, LI MEILIN, LIU ZHI, YANG SONGKUN, JIN FEI, WANG SHUXIANG, LIM WOO-JUN, ZHU YAN, ZUO XIBING, LIU XIAO
Принадлежит:

The invention provides an inland water body extraction method fused with void space pyramid pooling. The method comprises the following steps: constructing a water body extraction network; the water body extraction network adopts a SegFormer network as a framework, and decoders in the SegFormer network are improved to obtain new decoders; the new decoder comprises a first 1 * 1 convolution layer, an ASPP module, a first up-sampling module and a semantic fusion module which are connected in sequence from top to bottom; an input remote sensing image enters a new decoder to be processed after being subjected to feature extraction through an encoder; wherein the semantic fusion module fuses a feature map extracted from the bottommost layer in the encoder and a feature map output by the first up-sampling module and outputs the fused feature map as a water body extraction result; training the water body extraction network to obtain a water body extraction network model; and performing water body ...

Подробнее
Номер записи: 5