Narrowband Aircraft Targets Feature Extraction and Classification Based on Time-frequency Analysis
ZHAO Yue①② CHEN Zhichun③ JIU Bo①② ZHANG Lei①② LIU Hongwei①② LI Zhenfang①②
①(National Laboratory of Radar Signal Processing, Xidian University, Xi’an 710071, China) ②(Collaborative Innovation Center of Information Sensing and Understanding at Xidian University, Xi’an 710071, China) ③(Shanghai Astronomical Observatory, Chinese Academy of Sciences, Shanghai 200030, China)
Abstract:A new feature extraction method based on time-frequency analysis is proposed for aircraft targets classification under low signal-to-noise ratio. This method uses the variances of time-domain modulation periods of jet aircraft, propeller aircraft and helicopter to extract the variation of entropy in the time-frequency domain and gives a way to select optimal window lengths. Experimental result based on simulated data and measured data demonstrates that the proposed method can significantly improve the classification probability of aircraft targets under low signal-to-noise ratio.
YANG Shoufeng, WU Haikun, WANG Xiao, et al. Target feature extraction and recognition based on low-resolution radar[J]. Electronic Warfare Technology, 2015, 30(4): 15-20. doi: 10.3969/j.issn.1674-2230.2015.04.004.
[4]
符婷. 基于微多普勒特征的目标分类方法研究[D]. [硕士论文], 西安电子科技大学, 2011.
FU Ting. Research on classification of target based on Micro-Doppler[D]. [Master dissertation], Xidian University, 2011.
GUAN Yongsheng, ZUO Qunsheng, and LIU Hongwei. Micro-Doppler signature based cone-shaped target recognition[J]. Chinese Journal of Radio Science, 2011, 26(2): 209-215. doi: 10.13443/j.cjors.2011.02.023.
GUAN Yongsheng and ZUO Qunsheng. Eigenvalue spectrum signature based cone-shaped target recognition[J]. Journal of China Academy of Electronics and Information Technology, 2014, 9(2): 556-559. doi: 10.3969/j.issn. 1673-5692.2014.02. 010.
DU Lan, LI Linsen, LI Weilu, et al. Aircraft target classification based on correlation features from time-domain echoes[J]. Journal of Radars, 2015, 4(6): 621-629. doi: 10. 12000/JR15117.
PANG Cunsuo, LIU Lei, and SHAN Tao. Time-frequency analysis method based on short-time fractional fourier Transform[J]. Acta Electronica Sinica, 2014, 42(2): 347-352. doi: 10.3969/j.issn.0372-2112.2014.02.021.
LI Qingzhong, LI Ruiqin, LI Ming, et al. A target detection algorithm of HFSWR based on time-frequency analysis[J]. Chinese Journal of Radio Science, 2015, 30(5): 943-950. doi: 10.13443/j.cjors.2014112701.
YU Wanyou, YANG Guangyu, and ZHAO Hongli. A new method for ship length estimation based on Doppler spectrum analysis[J]. Radar Science and Technology, 2015, 13(5): 522-526. doi: 10.3969/j.issn.1672-2337.2015.05.013.
[12]
张艳丽. 高维数据下的判别分析及模型选择方法[D]. [博士论文], 山东大学, 2015.
ZHANG Yanli. Discriminant analysis and model selection method for high dimensional data[D]. [Ph.D. dissertation], Shandong University, 2015.
HAN Xun, DU Lan, LIU Hongwei, et al. Classification of micro-motion form of space cone-shaped objects based on time-frequency distribution[J]. System Engineering and Electronics, 2013, 35(4): 684-691. doi: 10.3969/j.issn.1001- 506X.2013.04.02.
[14]
CHRYSOSTOMOU C and SEKER H. Structural classification of protein sequences based on signal processing and support vector machines[C]. IEEE Engineering in Medicine and Biology Society, Orlando, FL, USA, 2016: 3088-3091. doi: 10.1109/EMBC.2016.7591382.
[15]
PANTELIS B, SERGIOS T, CHARALAMPOS M, et al. Complex support vector machines for regression and quaternary classification[J]. IEEE Transactions on Neural Networks and Learning Systems, 2015, 26(6): 1260-1274. doi: 10.1109/TNNLS.2014.2336679.