遥感目标检测方法、装置、电子设备及存储介质

By fusing convolutional neural networks with window attention mechanisms, the problems of accuracy and diversity in target detection in remote sensing images were solved, and efficient detection of target objects in high-volume, large-format remote sensing images was achieved.

CN116523842BActive Publication Date: 2026-07-17INST OF SEMICONDUCTORS - CHINESE ACAD OF SCI
View PDF 1 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
INST OF SEMICONDUCTORS - CHINESE ACAD OF SCI
Filing Date
2023-03-31
Publication Date
2026-07-17

Smart Images

  • Figure CN116523842B_ABST
    Figure CN116523842B_ABST
Patent Text Reader

Abstract

本公开提供了一种遥感目标检测方法、装置、电子设备及存储介质，可以应用于图像处理技术领域。该方法包括：利用卷积神经网络的不同特征提取支路对目标遥感图像进行特征提取，得到多个特征图；对多个特征图分别进行通道转换，得到与多个特征图分别对应的转换图，得到多个转换图；利用基于自注意力机制的网络对多个转换图和目标遥感图像进行特征提取，得到多个目标特征图；根据多个目标特征图，检测目标遥感图像中的目标对象。
Need to check novelty before this filing date? Find Prior Art