Classification and Recognition Method of Non-Cooperative Objects Based on Deep Learning
Zhengjia Wang,
Yi Han,
Yiwei Zhang,
Junhua Hao,
Yong Zhang
Affiliations
Zhengjia Wang
Institute of Precision Acousto-Optic Instrument, School of Instrumentation Science and Engineering, Harbin Institute of Technology, Harbin 150080, China
Yi Han
Institute of Precision Acousto-Optic Instrument, School of Instrumentation Science and Engineering, Harbin Institute of Technology, Harbin 150080, China
Yiwei Zhang
Institute of Precision Acousto-Optic Instrument, School of Instrumentation Science and Engineering, Harbin Institute of Technology, Harbin 150080, China
Junhua Hao
School of Precision Instruments and Opto-Electronics Engineering, Key Lab of Optoelectronic Information Technology (Ministry of Education), and Key Lab of Micro-Opto-Electro-Mechanical Systems (MOEMS) Technology (Ministry of Education), Tianjin University, Tianjin 300072, China
Yong Zhang
National Key Laboratory of Science and Technology on Tunable Laser, Harbin Institute of Technology, Harbin 150080, China
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%.
