窄带舰船目标识别方法研究

doi:10.16180/j.cnki.issn1007-7820.2021.06.009

摘要/Abstract

摘要：

文中针对窄带雷达舰船目标识别问题,提出了一种窄带雷达舰船目标识别方法。该方法从窄带雷达回波信号中提取目标的感兴趣区域,基于感兴趣区域提取目标的期望、标准差、方差、中心矩特征。依据雷达舰船目标航迹信息提取目标姿态角,并将姿态角作为特征引入到分类器中。最后,利用支持向量机方法对窄带雷达舰船目标进行分类。通过建立的仿真数据进行识别效果测试,实验结果表明该方法对舰船大、中、小分类具有较高的识别率,说明该方法具有一定的工程应用价值。

关键词: 窄带雷达, 舰船分类, 感兴趣区域, 期望, 标准差, 方差, 中心矩, 姿态角, 支持向量机

Abstract:

A ship target recognition method based on narrowband radar is proposed in the present study. This method extracts the region of interest of the target from the echo signal of narrowband radar, then extracts the characteristics of expectation, standard deviation, variance and central moment of the target based on the region of interest. According to the track information of the radar ship target, the proposed method extracts the attitude angle of the target and introduces the attitude angle as the feature into the classifier. Finally, the narrowband radar ship target is classified using the support vector machine. The results show that the method has a high recognition rate for large, medium and small ship classification, and it has a certain engineering application value.

Key words: narrowband radar, ship classification, region of interest, expect, standard deviation, variance, central moment, attitude angle, support vector machine

中图分类号:

TN957.52

张朋飞,魏存伟,刘先康,刘安然,杨欧,林永霖. 窄带舰船目标识别方法研究[J]. 电子科技, 2021, 34(6): 50-55.

ZHANG Pengfei,WEI Cunwei,LIU Xiankang,LIU Anran,YANG Ou,LIN Yonglin. Research on Ship Target Recognition Method of Narrowband Radar[J]. Electronic Science and Technology, 2021, 34(6): 50-55.

图/表 8

图1

图2

图3

图4

图5

图6

图7

表1

参考文献 20

[1]	田曙光, 田西兰. 一种窄带雷达舰船目标分类的决策方法[J]. 雷达科学与技术, 2016,14(2):159-162.
	Tian Shuguang, Tian Xilan. A decision-making algorithm of ship target classification for narrow band radar[J]. Radar Science and Technology, 2016,14(2):159-162.
[2]	魏文博, 蔡红军. 基于支持向量机的窄带雷达弹道导弹目标识别技术[J]. 电子科技, 2016,29(6):75-78.
	Wei Wenbo, Cai Hongjun. Narrowband radar ballistic missile target recognition technology based on SVM[J]. Electronic Science and Technology, 2016,29(6):75-78.
[3]	蒙继东, 尚社. 基于贝叶斯压缩感知的自旋目标成像[J]. 电子科技, 2017,30(2):94-97.
	Meng Jidong, Shang She. Spinning target imaging based on bayesian compressive sensing[J]. Electronic Science and Technology, 2017,30(2):94-97.
[4]	章建成, 苏涛. 一种新的窄带雷达高速机动多目标检测算法[J]. beoplay体育提现学报, 2017,44(2):20-26.
	Zhang Jiancheng, Su Tao. Novel detection algorithm for high-speed maneuvering multi-target with narrowband radar[J]. Journal of Xidian University, 2017,44(2):20-26.
[5]	韩勋, 杜兰, 刘宏伟. 窄带雷达观测下的锥体目标参数估计方法[J]. beoplay体育提现学报, 2015,42(6):43-48.
	Han Xun, Du Lan, Liu Hongwei. Parameter estimation method for the cone-shaped target under narrow-band radar observation[J]. Journal of Xidian University, 2015,42(6):43-48.
[6]	尹学庆. 隐马尔科夫模型在雷达目标识别中的应用研究[D]. 哈尔滨:哈尔滨工业大学, 2018.
	Yin Xueqing. Research on the application of hidden markov model in radar target recognition[D]. Harbin:Harbin Institute of Technology, 2018.
[7]	王锦章, 徐冰超, 任杰, 等. 一种基于Gabor变换的HRRP目标识别方法[J]. 电子科技, 2017,30(4):19-21.
	Wang Jinzhang, Xu Bingchao, Ren Jie, et al. A new method based on Gabor transform for HRRP target recognition[J]. Electronic Science and Technology, 2017,30(4):19-21.
[8]	魏存伟, 刘先康, 孙菲, 等. 一种基于雷达HRRP的舰船目标识别方法[J]. 电子科技, 2017,30(11):13-15,30.
	Wei Cunwei, Liu Xiankang, Sun Fei, et al. A method of ship target recognition based on HRRP[J]. Electronic Science and Technology, 2017,30(11):13-15,30.
[9]	柴晶, 刘宏伟, 保铮. 提高雷达HRRP目标识别和拒判性能的核学习算法[J]. beoplay体育提现学报, 2009,36(5):793-800.
	Chai Jing, Liu Hongwei, Bao Zheng. New kernel learning method to improve radar HRRP target recognition and rejection performance[J]. Journal of Xidian University, 2009,36(5):793-800.
[10]	王锦章, 魏存伟, 刘先康, 等. 基于Relax散射点特征提取的舰船目标识别方法[J]. 电子科技, 2011,24(4):8-11.
	Wang Jinzhang, Wei Cunwei, Liu Xiankang, et al. Ship target recognition based on Relax algorithm[J]. Electronic Science and Technology, 2011,24(4):8-11.
[11]	Guo Y, Xiao H T, Kan Y Z, et al. Learning using privileged information for HRRP-based radar target recognition[J]. IET Signal Processing, 2018,12(2):188-197. doi: 10.1049/sil2.v12.2
[12]	Peng P, Guo L X, Tong C M. An EM model for radar multipath simulation and HRRP analysis of low altitude target above electrically large composite scale rough surface[J]. Electromagnetics, 2018,38(3):177-188. doi: 10.1080/02726343.2018.1446714
[13]	Guo C, He Y, Wang H P, et al. Radar HRRP target recognition based on deep one-dimensional residual-inception network[J]. IEEE Access, 2019(7):9191-9204.
[14]	Li L, Liu Z. Noise-robust HRRP target recognition method via sparse-low-rank representation[J]. Electronics Letters, 2017,53(24):1602-1604. doi: 10.1049/ell2.v53.24
[15]	Li Q S, Xie W X. Target classification with low-resolution surveillance radars based on multifractal features[J]. Progress in Electromagnetics Research, 2012,45(7):291-308. doi: 10.2528/PIER03082502
[16]	李青, 李斌, 胡文俊, 等. 基于低分辨率雷达的海面舰船目标分类识别技术[J]. 现代雷达, 2012,34(12):45-49.
	Li Qing, Li Bin, Hu Wenjun, et al. Ship target classification based on the low bandwidth marine radar[J]. Modern Radar, 2012,34(12):45-49.
[17]	魏存伟, 段发阶, 刘先康, 等. 雷达舰船目标HRRP成像视角参数估计[J]. 系统工程与电子技术, 2019,41(12):2723-2729.
	Wei Cunwei, Duan Fajie, Liu Xiankang, et al. HRRP viewing angle parameter estimation of radar ship targets[J]. Systems Engineering and Electronics, 2019,41(12):2723-2729.
[18]	魏存伟, 段发阶, 刘先康. 基于宽带雷达HRRP舰船目标长度估计算法[J]. 系统工程与电子技术, 2018,40(9):1960-1965.
	Wei Cunwei, Duan Fajie, Liu Xiankang. Length estimation method of ship target based on wide-band radar’s HRRP[J]. Systems Engineering and Electronics, 2018,40(9):1960-1965.
[19]	赵东波, 李辉. 基于中心矩特征和GA-BP神经网络的雷达目标识别[J]. 红外与激光工程, 2018,47(8):384-390.
	Zhao Dongbo, Li Hui. Radar target recognition based on central moment feature and GA-BP neural network[J]. Infrared and Laser Engineering, 2018,47(8):384-390.
[20]	李航. 统计学习方法[M]. 北京:清华大学出版社, 2012.
	Li Hang. Statistical learning methods[M]. Beijing:Tsinghua University Press, 2012.

目标	样本1识别率	样本2识别率	样本3识别率
大型目标	81.66%	85.46%	87.28%
中型目标	74.36%	78.84%	84.53%
小型目标	86.32%	89.78%	93.02%
平均识别率	80.80%	84.70%	88.30%