采用多任务稀疏学习的雷达HRRP小样本目标识别

doi:10.3969/j.issn.1001-2400.2016.02.005

Abstract

Abstract:

A statistical modeling method based on multitask sparse learning is proposed to realize the recognition of the high resolution range profile (HRRP) with a small training data size. The statistical modeling of each training aspect-frame is considered as a single task in our method. Since the training aspect-frames are not independent but inter-related, they can share a compact dictionary to make full use of the information. However, with the different targets and the aspect sensitivity of the same target, it is usually hard to assess the task relatedness, and joint learning with unrelated tasks may degrade the recognition performance. Therefore, we adopt the Bernoulli-Beta prior to learn the needed atoms of each aspect-frame automatically with the given training data. Then the relatedness between frames is determined by the number of shared atoms, and multitask learning can be realized adaptively. The recognition experiments of the measured HRRP data demonstrate the performance of the proposed method.

Key words: radar target recognition, HRRP, sparse Bayesian, multitask learning

XU Danlei;DU Lan;WANG Penghui;LIU Hongwei. Radar HRRP target recognition by utilizing multitask sparse learning with a small training data size[J].Journal of Xidian University, 2016, 43(2): 23-28.

[1]	GUO Zekun,TIAN Long,HAN Ning,WANG Penghui,LIU Hongwei,CHEN Bo. Radar HRRP based few-shot target recognition with CNN-SSD [J]. Journal of Xidian University, 2021, 48(2): 7-14.
[2]	ZHANG Chaozhu,WANG Yu,JING Fulong. Hop timing estimation method by exploiting sparse Bayesian inference [J]. Journal of Xidian University, 2019, 46(3): 39-44.
[3]	WANG Yong;QIAO Qianqian;YANG Xiaoyu;XU Wenjuan;JIA Zheng;CHEN Chuchu;GAO Quanxue. Sparse Bayesian reconstruction combined with self-adaptive dictionary learning [J]. Journal of Xidian University, 2016, 43(4): 1-4+122.
[4]	JIN Biao;SU Tao;LI Yanyan;ZHANG Long. Multi-target tracking algorithm aided by a high resolution range profile [J]. J4, 2016, 43(1): 1-6+29.
[5]	XIONG Lin;JIAO Licheng;MAO Shasha . Selective ensemble based on the integer matrix linear transformation and its application to radar target recognition [J]. J4, 2015, 42(2): 13-19.
[6]	LI Zhipeng;MA Tianxiang;DU Lan;XU Danlei;LIU Hongwei;ZHANG Zijing. Multi-class classifier design for feature fusion in radar HRRP recognition [J]. J4, 2013, 40(1): 111-117.
[7]	WANG Penghui;DU Lan;LIU Hongwei;LI Yanbing;WU Zhaoping. New frame segmentation method for radar HRRPs [J]. J4, 2011, 38(6): 22-29.
[8]	GUANG Yongsheng;ZUO Qunsheng;LIU Hongwei;DU Lan;LI Yanbing. Micro-motion characteristic analysis and recognition of cone-shaped targets [J]. J4, 2011, 38(2): 105-111.
[9]	LI Li-ya;LIU Hong-wei;JIU Bo;WU Shun-jun. Polarization radar HRRP recognition based on the kernel function [J]. J4, 2010, 37(1): 49-55.
[10]	CHAI Jing;LIU Hong-wei;BAO Zheng. New kernel learning method to improve radar HRRP target recognition and rejection performance [J]. J4, 2009, 36(5): 793-800.
[11]	CHEN Feng;HOU Qing-yu;LIU Hong-wei;BAO Zheng. New adaptive angular-sector segmentation algorithm for radar ATR based on HRRP [J]. J4, 2009, 36(3): 410-417.
[12]	HOU Qing-yu;LIU Hong-wei;BAO Zheng. New method for suppression of the clutter of the wideband target recognition radar [J]. J4, 2008, 35(5): 769-773.
[13]	LIANG Hai-tao;TONG Chuang-ming;WANG Xiao-dan. SVM target identification method based on polarization HRRP [J]. J4, 2007, 34(7): 148-151.
[14]	CAO Xiang-hai;LIU Hong-wei;WU Shun-jun. Data lengthening and improved NFL classifier for HRRP recognition [J]. J4, 2007, 34(6): 930-934.
[15]	CHEN Feng;DU Lan;BAO Zheng. Modified KNN rule with its application in radar HRRP target recognition [J]. J4, 2007, 34(5): 681-686.

Radar HRRP target recognition by utilizing multitask sparse learning with a small training data size

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Metrics

Comments

Recommended 10