基于DTCWT-VAE的弹道中段目标RCS识别

doi:10.12305/j.issn.1001-506X.2024.07.10

摘要/Abstract

摘要：

针对弹道目标雷达信号易受环境影响、目标识别准确率低的问题, 提出了一种基于双树复小波变换(dual-tree complex wavelet transform, DTCWT)和变分自编码器(variational autoencoder, VAE)的弹道目标雷达散射截面(radar cross section, RCS)识别法。首先, 采用DTCWT对弹道目标RCS动态数据进行预处理, 再利用VAE提取目标的隐变量特征, 最后用支持向量机(support vector machine, SVM)分类器进行识别。实验结果表明, 与已有方法相比, 该方法具有更高的识别概率, 且鲁棒性较好。

关键词: 弹道目标, 目标识别, 雷达散射截面, 双树复小波变换, 变分自编码器

Abstract:

Aiming at the problem that the radar signal of ballistic target is easily affected by the environment and the target recognition accuracy is low, a radar cross section (RCS) recognition method of ballistic target based on dual-tree complex wavelet transform (DTCWT) and variational autoencoder (VAE) is proposed. Firstly, the dynamic datas of ballistic target RCS are preprocessed by DTCWT. Then, the hidden variable features of target are extracted by VAE. Finally, the support vector machine (SVM) classifier is used to identify the data. Experimental results show that compared with the existing methods, the proposed method has higher recognition probability and better robustness.

Key words: ballistic target, target recognition, radar cross section (RCS), dual-tree complex wavelet transform (DTCWT), variational autoencoder (VAE)

中图分类号:

TN957

王彩云, 张慧雯, 王佳宁, 吴钇达, 常韵. 基于DTCWT-VAE的弹道中段目标RCS识别[J]. 系统工程与电子技术, 2024, 46(7): 2269-2275.

Caiyun WANG, Huiwen ZHANG, Jianing WANG, Yida WU, Yun CHANG. Ballistic midcourse target RCS recognition based on DTCWT-VAE[J]. Systems Engineering and Electronics, 2024, 46(7): 2269-2275.

图/表 7

图1

图2

图3

表1

图4

表2

图5

参考文献 40

1	LI C W, XIE B, PEI Y. A RCS periodicity extraction algorithm for ballistic target[C]//Proc. of the International Conference on Image, Vision and Intelligent Systems, 2022: 1207-1216.
2	ZHAO C C , WANG L , LIU Y M . Ballistic target recognition based on 4-D point cloud using randomized stepped frequency radar[J]. IEEE Trans.on Aerospace and Electronic Systems, 2022, 58 (6): 5711- 5729. doi: 10.1109/TAES.2022.3178971
3	胡玉颖, 刘丙杰, 马子涵. 美国反导系统预警雷达网能力分析[J]. 舰船电子工程, 2022, 42 (4): 11-13, 25.
	HU Y Y , LIU B J , MA Z H . Analysis of early warning radar network capabilities of U.S. anti-missile systems[J]. Ship Elec-tronic Engineering, 2022, 42 (4): 11-13, 25.
4	韩晋山, 邢建平, 张浩, 等. 美国导弹预警系统的发展现状与趋势分析[J]. 科技导报, 2019, 37 (4): 91- 95.
	HAN J S , XING J P , ZHANG H , et al. Development of American missile early warning system[J]. Science & Technology Review, 2019, 37 (4): 91- 95.
5	SCHULTZ K, DAVIDSON S, STEIN A, et al. Range Doppler laser radar for midcourse discrimination-the firefly experiments[C]//Proc. of the Annual Interceptor Technology Conference, 1993.
6	黄小红, 马云, 陈曾平. 利用RCS序列估计空间目标尺寸的方法研究[J]. 信号处理, 2005, 21 (6): 639- 641.
	HUANG X H , MA Y , CHEN Z P . Research on size of space object estimated from RCS[J]. Journal of Signal Processing, 2005, 21 (6): 639- 641.
7	冯德军, 王雪松, 徐振海, 等. 基于ESPRIT的中段弹道目标特征提取方法[J]. 国防科技大学学报, 2004, 26 (2): 41- 45.
	FENG D J , WANG X S , XU Z H , et al. A study of the midcourse ballistic target signatures extracting based on ESPRIT[J]. Journal of National University of Defense Technology, 2004, 26 (2): 41- 45.
8	陈行勇, 黎湘, 郭桂蓉, 等. 微进动弹道导弹目标雷达特征提取[J]. 电子与信息学报, 2006, 28 (4): 643- 646.
	CHEN H Y , LI X , GUO G R , et al. Radar feature extraction of micro-precession ballistic missile warhead[J]. Journal of Electronics & Information Technology, 2006, 28 (4): 643- 646.
9	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. doi: 10.1109/ACCESS.2019.2891594
10	XIANG Q , WANG X D , LAI J , et al. Multi-scale group-fusion convolutional neural network for high-resolution range profile target recognition[J]. IET Radar, Sonar & Navigation, 2022, 16 (12): 1997- 2016.
11	LI X X , YAO H Y , SUN W F . A new compensation method of HRRP for ballistic targets[J]. Advanced Materials Research, 2013, 756-759, 3860- 3864. doi: 10.4028/www.scientific.net/AMR.756-759.3860
12	PERSICO A R , ILIOUDIS C V , CLEMENTE C , et al. Novel classification algorithm for ballistic target based on HRRP frame[J]. IEEE Trans.on Aerospace and Electronic Systems, 2019, 55 (6): 3168- 3189. doi: 10.1109/TAES.2019.2905281
13	UVANNI L A, RAINEY T G, BALASUBRAMANIAN U, et al. Neural network for intelligent query of an FBI forensic database[C]//Proc. of the Command, Control, Communications, and Intelligence Systems for Law Enforcement, 1997: 16-19.
14	李文臣, 王涛, 王雪松, 等. 旋转对称目标章动参数全极化测量研究[J]. 兵工学报, 2010, 31 (8): 1041- 1047.
	LI W C , WANG T , WANG X S , et al. Research on fully polarization measurement of nutation parameters of rotary symmetric target[J]. Acta Armamentarii, 2010, 31 (8): 1041- 1047.
15	CHENG X, LIU Y, LI Y Z, et al. Ballistic target discrimination based on polarimetric entropy[C]//Proc. of the IEEE CIE International Conference on Radar, 2011: 1390-1393.
16	YANG H , ZHANG Y S , DING W Z . A fast recognition method for space targets in ISAR images based on local and global structural fusion features with lower dimensions[J]. International Journal of Aerospace Engineering, 2020, 2020, 3412582.
17	SUN J J , TONG C M , ZHANG M M . Feature extraction of ballistic midcourse target from ISAR imaging[J]. ICIC Express Letters, 2015, 9 (6): 1769- 1776.
18	JIN G H , GAO X Z , DONG Z . Two-dimensional length extraction of ballistic target from ISAR images using a new scaling method by affine registration[J]. Defence Science Journal, 2014, 64 (5): 458- 463. doi: 10.14429/dsj.64.5001
19	PALADINI R , MARTORELLA M , BERIZZI F . Classification of man-made targets via invariant coherency-matrix eigenvector decomposition of polarimetric SAR/ISAR images[J]. IEEE Trans.on Geoscience and Remote Sensing, 2011, 49 (8): 3022- 3034. doi: 10.1109/TGRS.2011.2116121
20	TANG W B, YU L, WEI Y S, et al. Radar target recognition of ballistic missile in complex scene[C]//Proc. of the IEEE International Conference on Signal, Information and Data Processing, 2019.
21	CAI T T, SHENG Y J, HE Z, et al. Classification and recognition of ballistic microcephalus based on deep neural network[C]//Proc. of the International Applied Computational Electromagnetics Society Symposium, 2019.
22	PERSICO A R , CLEMENTE C , GAGLIONE D , et al. On model, algorithms, and experiment for micro-Doppler-based recognition of ballistic targets[J]. IEEE Trans.on Aerospace and Electronic Systems, 2017, 53 (3): 1088- 1108. doi: 10.1109/TAES.2017.2665258
23	SUN H X , ZHENG L , NING X . Ballistic missile warhead recognition based on micro-Doppler frequency[J]. Defence Science Journal, 2008, 58 (6): 705- 709. doi: 10.14429/dsj.58.1697
24	YAO H Y, LI X X, SUN W F, et al. Micro-Doppler analysis of nutation target in ballistic midcourse[C]//Proc. of the IET International Radar Conference, 2013.
25	SHENG J . Target identity recognition method based on RCS distribution and spatial location[J]. Procedia Computer Science, 2019, 147, 632- 637. doi: 10.1016/j.procs.2019.01.192
26	WEN B Q, WANG T, CHENG K. Simulation research on dynamic RCS characteristics of cruise missile[C]//Proc. of the IOP Conference Series: Earth and Environmental Science, 2019, 300(2): 022170.
27	LEI X H, FU X J, WANG C, et al. Statistical feature selection of narrowband RCS sequence based on greedy algorithm[C]//Proc. of the IEEE CIE International Conference on Radar, 2011: 1664-1667.
28	WEI N , ZHANG L M , ZHANG X G . A weighted decision-level fusion architecture for ballistic target classification in midcourse phase[J]. Sensors, 2022, 22 (17): 6649. doi: 10.3390/s22176649
29	CHOI I O , PARK S H , KIM M , et al. Efficient discrimination of ballistic targets with micromotions[J]. IEEE Trans.on Aerospace and Electronic Systems, 2019, 56 (2): 1243- 1261.
30	YANG L, ZHANG W P, JIANG W D. Ballistic target recognition based on deep learning by utilizing the micro-Doppler feature[C]//Proc. of the IEEE 6th Advanced Information Technology, Electronic and Automation Control Conference, 2022: 1628-1632.
31	SHI D Y, LIN Q, HU B, et al. Research on radar target recognition method based on deep learning[C]//Proc. of the International Conference on Artificial Intelligence, Virtual Reality, and Visualization, 2021: 82-89.
32	LI S Y, YANG T, LI M M, et al. Inertia ratio parameter extraction of typical ballistic target based on deep learning[C]//Proc. of the International Applied Computational Electromagnetics Society Symposium, 2021.
33	XU X G , FENG C Q , HAN L X . Classification of radar targets with micro-motion based on RCS sequences encoding and convolutional neural network[J]. Remote Sensing, 2022, 14 (22): 5863. doi: 10.3390/rs14225863
34	李江, 冯存前, 王义哲, 等. 基于深度学习的弹道目标智能分类[J]. 系统工程与电子技术, 2020, 42 (6): 1226- 1234. doi: 10.3969/j.issn.1001-506X.2020.06.04
	LI J , FENG C Q , WANG Y Z , et al. Intelligent classification of ballistic targets based on deep learning[J]. Systems Engineering and Electronics, 2020, 42 (6): 1226- 1234. doi: 10.3969/j.issn.1001-506X.2020.06.04
35	郭继光, 李奇峰. 基于迁移学习的小样本弹道导弹目标识别方法[J]. 中国电子科学研究院学报, 2022, 17 (7): 626- 634.
	GUO J G , LI Q F . Research on ballistic missile target recognition based on transfer learning for small samples[J]. Journal of China Academy of Electronics and Information Technology, 2022, 17 (7): 626- 634.
36	王彩云, 黄盼盼, 李晓飞, 等. 基于AEPSO-SVM算法的雷达HRRP目标识别[J]. 系统工程与电子技术, 2019, 41 (9): 1984- 1989. doi: 10.3969/j.issn.1001-506X.2019.09.10
	WANG C Y , HUANG P P , LI X F , et al. Radar HRRP target recognition based on AEPSO-SVM algorithm[J]. Systems Engineering and Electronics, 2019, 41 (9): 1984- 1989. doi: 10.3969/j.issn.1001-506X.2019.09.10
37	SELESNICK I W , BARANIUK R G , KINGSBURY N G . The dual tree complex wavelet transform[J]. IEEE Signal Processing Magazine, 2005, 22 (6): 123- 151. doi: 10.1109/MSP.2005.1550194
38	KARINE A, TOUMI A, KHENCHAF A, et al. A non-Gaussian statistical modeling of SIFT and DTCWT for radar target recognition[C]//Proc. of the IEEE/ACS 13th International Conference of Computer Systems and Applications, 2016.
39	Al-NAAMI B , FRAIHAT H , Al-NABULSI J , et al. Assessment of dual-tree complex wavelet transform to improve SNR in collaboration with neuro-fuzzy system for heart-sound identification[J]. Electronics, 2022, 11 (6): 938. doi: 10.3390/electronics11060938
40	KINGMA D P, WELLING M. Auto-encoding variational Bayes[C]//Proc. of the International Conference on Learning, 2014.

类别	自旋频率/Hz	进动频率/Hz	进动角/(°)	章动频率/Hz	章动角/(°)	翻滚频率/Hz	翻滚角/(°)
弹头	1.5	2∶0.5∶4	3∶0.375∶4.5	—	—	—	—
诱饵1	3	2.5∶0.5∶4.5	5∶0.375∶6.5	1	2	—	—
诱饵2	2	1.5∶0.5∶3.5	4∶0.375∶5.5	0.5	1	—	—
碎片	—	—	—	—	—	2∶1∶6	70∶5∶90

方法名称	准确率				平均准确率
方法名称	弹头	诱饵1	诱饵2	碎片	平均准确率
11种统计特征-PCA^[28]-AdaBoostM2	79.15	90.06	85.55	95.96	87.68
11种统计特征-PCA^[28]-SVM	84.72	91.39	86.31	96.30	89.68
9种特征^[35]-AdaBoostM2	84.55	80.42	86.67	93.88	86.43
9种特征^[35]-SVM	79.72	90.86	88.19	94.46	88.31
本文方法	92.65	95.96	97.02	99.70	96.33

[1]	吴钇达, 王彩云, 王佳宁, 李晓飞. 基于ISVM-DS的红外多传感器融合识别方法[J]. 系统工程与电子技术, 2024, 46(5): 1555-1560.
[2]	曾舒雅, 饶彬. 基于动力学守恒定律的弹道目标关联方法[J]. 系统工程与电子技术, 2024, 46(2): 684-691.
[3]	王湖升, 陈伯孝, 叶倾知. 基于箔条干扰实测数据的对抗方法研究[J]. 系统工程与电子技术, 2023, 45(7): 2010-2021.
[4]	王哲昊, 简涛, 黄晓冬, 王海鹏, 刘瑜. 基于角域特征PSO的海面目标HRRP识别方法[J]. 系统工程与电子技术, 2023, 45(6): 1642-1650.
[5]	黄瀚仪, 胡仕友, 郭胜龙, 李珊君, 舒勤. 基于稀疏分解的海面微动目标识别[J]. 系统工程与电子技术, 2023, 45(4): 1016-1023.
[6]	李英俊, 刘永祥, 田彪, 张文鹏. 基于IRLS的跳频模式下GTD散射参数提取和RCS重构[J]. 系统工程与电子技术, 2023, 45(3): 678-689.
[7]	赵庆媛, 赵志强, 叶春茂, 鲁耀兵. 基于自注意力的双波段预警雷达微动融合识别[J]. 系统工程与电子技术, 2023, 45(3): 708-716.
[8]	刘丹阳, 吴堃, 朱永锋, 张永杰, 周剑雄. 地面目标HRRP识别的稳健性特征选择方法[J]. 系统工程与电子技术, 2023, 45(12): 3726-3733.
[9]	周剑雄, 朱永锋, 陈冀, 吴宏铭, 吴堃, 张永杰. SAR图像辅助的雷达目标距离像检测识别[J]. 系统工程与电子技术, 2023, 45(11): 3428-3436.
[10]	王宏安, 黄达, 张伟, 潘晔, 王祥丰, 邵怀宗, 顾杰. 基于DSGD的分布式电磁目标识别[J]. 系统工程与电子技术, 2023, 45(10): 3024-3031.
[11]	刘佳, 徐群玉, 陈唯实. 无人机雷达航迹运动特征提取及组合分类方法[J]. 系统工程与电子技术, 2023, 45(10): 3122-3131.
[12]	谢拥军, 高杰, 武沛羽, 牛立强. 有源RCS及其应用[J]. 系统工程与电子技术, 2022, 44(8): 2468-2473.
[13]	王彩云, 吴钇达, 王佳宁, 马璐, 赵焕玥. 基于改进的CNN和数据增强的SAR目标识别[J]. 系统工程与电子技术, 2022, 44(8): 2483-2487.
[14]	孙晶明, 虞盛康, 孙俊. 基于元学习的雷达小样本目标识别方法及改进[J]. 系统工程与电子技术, 2022, 44(6): 1839-1845.
[15]	周晓玲, 张朝霞, 鲁雅, 王倩, 王琨琨. 基于改进R-FCN的SAR图像识别[J]. 系统工程与电子技术, 2022, 44(4): 1202-1209.