Journal of Systems Engineering and Electronics ›› 2023, Vol. 34 ›› Issue (1): 19-27.doi: 10.23919/JSEE.2023.000002

• REMOTE SENSING • Previous Articles     Next Articles

Classification of birds and drones by exploiting periodical motions in Doppler spectrum series

Jia DUAN1(), Lei ZHANG1(), Yifeng WU1(), Yue ZHANG1,*(), Zeya ZHAO2(), Xinrong GUO3()   

  1. 1 School of Electronics and Communication, Sun Yat-Sen University, Shenzhen 518107, China
    2 Beijing Institute of Tracking and Telecommunication Technology, Beijing 100854, China
    3 Armed Police Engineering University, Xi’an 510507, China
  • Received:2022-04-07 Accepted:2022-10-18 Online:2023-02-18 Published:2023-03-03
  • Contact: Yue ZHANG E-mail:bifiduan119@126.com;zhanglei57@mail.sysu.edu.cn;wuyf95@mail.sysu.edu.cn;zhangyue_frog1@163.com;zzy_kelly@163.com;rapgxr@163.com
  • About author:
    DUAN Jia was born in 1989. She received her Ph.D. degree in signal processing from Xidian University in 2015. She worked for the Chinese Aviation Industry Corporation as a senior engineer in signal processing and target recognition from 2016 to 2021. Afterward, she works as an associate research fellow in the School of Electronics and Communication, Sun Yat-sen University. Her research interests include radar signal processing, ISAR imaging, SAR/ISAR feature extraction and target recognition. E-mail: bifiduan119@126.com

    ZHANG Lei was born in 1984. He received his B.S. degree from Chang’an University in 2006. He received his Ph.D. degree from Xidian University in 2011. He worked in the National Key Lab of Radar Signal Processing from 2011 to 2019. Currently, he works as a professor in the School of Electronics and Communication, Sun Yat-sen University. His research interests include radar signal processing, SAR/ISAR imaging, SAR interpreting, electronic counter measures, etc. E-mail: zhanglei57@mail.sysu.edu.cn

    WU Yifeng was born in 1988. He received his B.S. and Ph.D. degrees from Xidian University in 2010 and 2016, respectively. He worked for the Chinese Aviation Industry Corporation as a senior engineer in signal processing and target detection from 2016 to 2020. Currently, He works as an associate professor in the School of Electronics and Communication, Sun Yat-sen University. His research interests include signal processing, space-time adaptive processing, radar target detection, and clutter suppression. E-mail: wuyf95@mail.sysu.edu.cn

    ZHANG Yue was born in 1980. He received his Ph.D. degree in electronic science and technology at National University of Defense Technology. He is now an associate professor in Sun Yat-sen University. His research interests include radar signal processing and automatic targets recognition. E-mail: zhangyue_frog1@163.com

    ZHAO Zeya received her M.S. degree in information engineering from Information Engineering University. She is now with Beijing Institute of Tracking and Transmission Technology. Her research interests include radar signal analysis and intelligence information processing. E-mail: zzy_kelly@163.com

    GUO Xinrong received her B.Sc. and M.Sc. degrees in radio science from Xidian University, Xian, China, in 2011 and 2014, respectively. She is currently a Lecturer with Armed police Engineering University, Xian, China. Her research interests include inverse synthetic aperture radar imaging and computational electromagnetics. E-mail: rapgxr@163.com
  • Supported by:
    This work was supported by the National Natural Science Foundation of China (62101603), the Shenzhen Science and Technology Program (KQTD20190929172704911), the Aeronautical Science Foundation of China (2019200M1001), the National Nature Science Foundation of Guangdong (2021A1515011979), the Guangdong Key Laboratory of Advanced IntelliSense Technology (2019B121203006), and the Pearl River Talent Recruitment Program (2019ZT08X751).

Abstract:

With the rapidly growing abuse of drones, monitoring and classification of birds and drones have become a crucial safety issue. With similar low radar cross sections (RCSs), velocities, and heights, drones are usually difficult to be distinguished from birds in radar measurements. In this paper, we propose to exploit different periodical motions of birds and drones from high-resolution Doppler spectrum sequences (DSSs) for classification. This paper presents an elaborate feature vector representing the periodic fluctuations of RCS and micro kinematics. Fed by the Doppler spectrum and feature sequence, the long to short-time memory (LSTM) is used to solve the time series classification. Different classification schemes to exploit the Doppler spectrum series are validated and compared by extensive real-data experiments, which confirms the effectiveness and superiorities of the proposed algorithm.

Key words: target classification, long-to-short memory (LSTM), drone discrimination, Doppler spectrum series