Classification and Recognition Method of Non-Cooperative Objects Based on Deep Learning

作     者：Wang, Zhengjia Han, Yi Zhang, Yiwei Hao, Junhua Zhang, Yong 

作者机构：Harbin Inst Technol Inst Precis Acousto Opt Instrument Sch Instrumentat Sci & Engn Harbin 150080 Peoples R China Tianjin Univ Sch Precis Instruments & Optoelect Engn Minist Educ Key Lab Optoelect Informat Technol Tianjin 300072 Peoples R China Tianjin Univ Key Lab MicrooptoElectroMech Syst MOEMS Technol Minist Educ Tianjin 300072 Peoples R China Tianjin Renai Coll Dept Phys Tianjin 301636 Peoples R China Harbin Inst Technol Natl Key Lab Sci & Technol Tunable Laser Harbin 150080 Peoples R China Harbin Inst Technol Sch Astronaut Dept Optoelect Informat Sci & Technol Harbin 150080 Peoples R China 

出 版 物：《SENSORS》 (传感器)

年 卷 期：2024年第24卷第2期

页      面：583页

核心收录：

学科分类：0710[理学-生物学] 071010[理学-生物化学与分子生物学] 0808[工学-电气工程] 07[理学] 0804[工学-仪器科学与技术] 0703[理学-化学] 

基　　金：National Natural Science Foundation of China (NSFC) [62371163, 11504079] Tianjin Research Innovation Project for Postgraduate Students [2022KJ048] Chinese Academy of Sciences (CAS) [U2031142] 

主　　题：non-cooperation target micro-Doppler effect laser coherence detection deep learning classification and recognition 

摘      要：Accurately classifying and identifying non-cooperative targets is paramount for modern space missions. This paper proposes an efficient method for classifying and recognizing non-cooperative targets using deep learning, based on the principles of the micro-Doppler effect and laser coherence detection. The theoretical simulations and experimental verification demonstrate that the accuracy of target classification for different targets can reach 100% after just one round of training. Furthermore, after 10 rounds of training, the accuracy of target recognition for different attitude angles can stabilize at 100%.