记笔记

Target detection of remote sensing images based on deep learning method and system

Wang Su JunPing Yi FanChen GangYang LiWen WeiXu Chang ZhiShao Ying Zhao

China Academy of Space Technology

摘要：With the rapid growth of remote sensing image data, it is very important to find a way to extract and recognize the target quickly and accurately from the massive remote sensing data. In recent years, the development of deep learning has provided an effective way for target detection of remote sensing images. This paper applies deep learning technology to target detection of remote sensing images, and constructs a target detection system software which integrates sample labeling, data set construction, pretreatment of training sample, training algorithm, migration learning,target recognition and post processing. It provides technical support to the tasks of classification, information extraction and change detection of remote sensing image. The experimental results show that the target recognition system of remote sensing images has high precision in the scene classification and specific target detection of high-resolution remote sensing images.

关键词：

deep learning; target detection; remote sensing images; system design;

基金：

supported by the National Natural Science Foundation of China （grant no. 61401526 and 61801377）；

会议名称：

2021 3rd International Conference on Advanced Information Science and System （AISS 2021）

会议时间：

2021-11-26

会议地点：

中国海南三亚