基于Tri-feature训练的目标与海杂波鉴别算法

doi:10.12305/j.issn.1001-506X.2024.09.05

摘要/Abstract

摘要：

针对海杂波背景下末制导雷达容易出现错误检测的问题, 开展海杂波抑制和鉴别研究。采用基于Tri-feature训练的目标鉴别分类算法, 以目标幅度、峰值持续范围和起伏率作为特征量, 核函数选择径向基函数(radial basis function, RBF)。RBF非线性映射能力强, 在高维空间中可以更好地表达数据之间的关系, 然后进行支撑向量机(support vector machine, SVM)目标鉴别分类器设计和实验数据验证。经公开的实测数据验证, 所提算法准确率达到97%以上。通过与传统的模板匹配识别方法进行对比, 基于Tri-feature训练的目标鉴别分类算法有更高的鉴别准确率, 证明了所提方法的有效性和先进性。

关键词: 海杂波抑制, 末制导雷达, 目标分类, 支持向量机

Abstract:

Focusing on the issue of error detection in terminal guidance radar under sea clutter background, research on sea clutter suppression and discrimination is conducted. The target identification and classification algorithm based on Tri-feature training is adopted, and the target amplitude, peak duration range and fluctuation rate are used as feature quantities. The radial basis function (RBF) is selected as the kernel function, which has strong nonlinear mapping ability and can better represent the relationship between data in high-dimensional space. Then, the support vector machine (SVM) target identification and classification classifier design and experimental data verification are carried out. Verified by publicly available measured data, the accuracy rate of the proposed algorithm has reached over 97%. Compared with the traditional template matching recognition method, the target identification and classification algorithm based on Tri-feature training has higher identification accuracy, which proves the effectiveness and progressiveness of the proposed method.

Key words: sea clutter suppression, terminal guidance radar, target classification, support vector machine (SVM)

中图分类号:

TP391

吴巍, 薛冰, 刘丹丹. 基于Tri-feature训练的目标与海杂波鉴别算法[J]. 系统工程与电子技术, 2024, 46(9): 2935-2940.

Wei WU, Bing XUE, Dandan LIU. Target and sea clutter identification algorithm based on Tri-feature training[J]. Systems Engineering and Electronics, 2024, 46(9): 2935-2940.

图/表 8

图1

图2

表1

表2

图3

表3

图4

表4

参考文献 30

1	FARSHCHIAN M, POSNER F L. The Pareto distribution for low grazing angle and high resolution X-band sea clutter[C]//Proc. of the IEEE Radar Conference, 2010: 789-793.
2	ROSENBERG L, BOCQUET S. The Pareto distribution for high grazing angle sea-clutter[C]//Proc. of the IEEE International Geoscience and Remote Sensing Symposium, 2013: 4209-4212.
3	WEINBERG G V . Assessing Pareto fit to high-resolution high-grazing-angle sea clutter[J]. Electronics Letters, 2011, 47 (8): 516- 517. doi: 10.1049/el.2011.0518
4	ROSENBERG L, WATTS S, BOCQUET S. Application of the K+Rayleigh distribution to high grazing angle sea-clutter[C]//Proc. of the International Radar Conference, 2014.
5	FICHE A , ANGELLIAUME S , ROSENBERG L , et al. Analysis of X-band SAR sea-clutter distributions at different grazing angles[J]. IEEE Trans.on Geoscience and Remote Sensing, 2015, 53 (8): 4650- 4660. doi: 10.1109/TGRS.2015.2405577
6	HU J , TUNG W , GAO J . A new way to model nonstationary sea clutter[J]. IEEE Signal Processing Letters, 2009, 16 (2): 129- 132. doi: 10.1109/LSP.2008.2009844
7	TSIHRINTZIS G A , NIKIAS C L . Evaluation of fractional, lower-order statistics-based detection algorithms on real radar sea-clutter data[J]. IEE Proceedings-Radar, Sonar & Navigation, 1997, 144 (1): 29- 37.
8	ZHOU H K , JIANG T . Decision tree based sea-surface weak target detection with false alarm rate controllable[J]. IEEE Signal Processing Letters, 2019, 26 (6): 793- 797. doi: 10.1109/LSP.2019.2909584
9	SONG J , CAI F Q , LIU H Y . SAR image detection of sea targets based on two-step CFAR detector of KK distribution[J]. The Journal of Engineering, 2019, 2019 (19): 5644- 5647. doi: 10.1049/joe.2019.0360
10	LIU H Y , SONG J , XIONG W , et al. Analysis of amplitude statistical and correlation characteristics of high grazing angle sea-clutter[J]. The Journal of Engineering, 2019, 2019 (20): 6829- 6833. doi: 10.1049/joe.2019.0494
11	LIU N B , XU Y A , TIAN Y H , et al. Background classification method based on seep learning for intelligent automotive radar target detection[J]. Future Generation Computer Systems, 2019, 94, 524- 535. doi: 10.1016/j.future.2018.11.036
12	LIU N B , JIANG X Y , DING H . Summary of research on characteristics of radar sea clutter and target detection at high grazing angles[J]. Journal of Electronics & Information Technology, 2021, 43 (10): 2771- 2780. doi: 10.11999/JEIT200451
13	LI J Y , SHUI P L , GUO Z X , et al. Fast principal component analysis-based detection of small targets in sea clutter[J]. IET Radar, Sonar & Navigation, 2022, 16 (8): 1282- 1291.
14	ZHANG K , SHUI P L , FENG Y . Detection of sea-surface small targets masked by range sidelobes of large objects[J]. IEEE Trans.on Aerospace and Electronic Systems, 2022, 58 (2): 1446- 1461. doi: 10.1109/TAES.2021.3116120
15	ZHANG K , SHUI P L . Estimation of complex high-resolution range profiles of ships by sparse recovery iterative minimization method[J]. IEEE Trans.on Aerospace and Electronic Systems, 2021, 57 (5): 3042- 3056. doi: 10.1109/TAES.2021.3068431
16	LI X , SHUI P L , ZHANG Z D , et al. External calibration of P-band island-based sea clutter measurement radar on the sea surface[J]. IEEE Trans.on Geoscience and Remote Sensing, 2021, 59 (7): 5711- 5720. doi: 10.1109/TGRS.2020.3023714
17	YU H , SHUI P L , LU K . Outlier-robust tri-percentile para-meter estimation of K-distributions[J]. Signal Processing, 2021, 181, 107906. doi: 10.1016/j.sigpro.2020.107906
18	XU S W , ZHU J N , JIANG J Z , et al. Sea-surface floating small target detection by multifeature detector based on isolation forest[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021, 14, 704- 715. doi: 10.1109/JSTARS.2020.3033063
19	LIANG X , SHUI P L , SU H T . Bi-phase compound-Gaussian mixture model of sea clutter and scene-segmentation-based target detection[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021, 14, 4661- 4674. doi: 10.1109/JSTARS.2021.3074172
20	SHUI P L , XIA X Y , ZHANG Y S . Sea-land segmentation in maritime surveillance radars via K-nearest neighbor classifier[J]. IEEE Trans.on Aerospace and Electronic Systems, 2020, 56 (5): 3854- 3867. doi: 10.1109/TAES.2020.2981267
21	LI X , SHUI P L , XIA X Y , et al. Analysis of UHF-band sea clutter reflectivity at low grazing angles in offshore waters of the Yellow Sea[J]. International Journal of Remote Sensing, 2020, 41 (19): 7472- 7485. doi: 10.1080/01431161.2020.1760395
22	YU H , SHUI P L , LU K , et al. Bipercentile parameter estimators of bias reduction for generalised Pareto clutter model[J]. IET Radar, Sonar & Navigation, 2020, 14 (7): 1105- 1112.
23	MOU X Q , CHEN X L , GUAN J , et al. Sea clutter suppression for radar PPI images based on SCS-GAN[J]. IEEE Geoscience and Remote Sensing Letters, 2021, 18 (11): 1886- 1890. doi: 10.1109/LGRS.2020.3012523
24	SHUI P L , LI D C , XU S W . Tri-feature-based detection of floating small targets in sea clutter[J]. IEEE Trans.on Aerospace and Electronic Systems, 2014, 50 (2): 1416- 1430. doi: 10.1109/TAES.2014.120657
25	张仁李, 盛卫星, 马晓峰. 基于最大似然差的智能恒虚警检测器[J]. 系统工程与电子技术, 2011, 33 (12): 2631- 2637. doi: 10.3969/j.issn.1001-506X.2011.12.12
	ZHANG R L , SHENG W X , MA X F . Intelligent CFAR detector based on maximum likelihood difference[J]. Systems Engineering and Electronics, 2011, 33 (12): 2631- 2637. doi: 10.3969/j.issn.1001-506X.2011.12.12
26	ROHMAN B P A, KURNIAWAN D, MIFTAHUSHUDUR M T. Switching CA/OS CFAR using neural network for radar target detection in nonhomogeneous environment[C]//Proc. of the IEEE International Electronics Symposium, 2015: 280-283.
27	WANG L , WANG D , HAO C . Intelligent CFAR detector based on support vector machine[J]. IEEE Access, 2017, 5, 26965- 26972. doi: 10.1109/ACCESS.2017.2774262
28	田玉芳, 尹志盈, 姬光荣. 基于SVM的海面弱目标检测[J]. 中国海洋大学学报, 2013, 43 (7): 104- 109.
	TIAN Y F , YIN Z Y , JI G R . Weak targets detection in sea clutter based on SVM[J]. Periodical of Ocean University of China, 2013, 43 (7): 104- 109.
29	苏宁远, 陈小龙, 关键, 等. 基于卷积神经网络的海上微动目标检测与分类方法[J]. 雷达学报, 2018, 7 (5): 565- 574.
	SU N Y , CHEN X L , GUAN J , et al. Detection and classification of maritime target with micro-motion based on CNNs[J]. Journal of Radars, 2018, 7 (5): 565- 574.
30	关键, 刘宁波, 王国庆, 等. 雷达对海探测试验与目标特性数据获取——海上目标双极化多海况散射特性数据集[J]. 雷达学报, 2023, 12 (2): 456- 469.
	GUAN J , LIU N B , WANG G Q , et al. Sea-detecting radar experiment and target feature data acquisition for dual polarization multistate scattering dataset of marine targets[J]. Journal of Radars, 2023, 12 (2): 456- 469.

幅度	峰值持续范围	起伏率	判断
8 437.07	5	0.073 5	1
7 947.44	5	0.058 0	1
7 739.83	3	0.026 1	1
5 837.99	3	0.245 7	1
5 496.30	3	0.058 5	1
4 644.88	4	0.154 9	1
4 640.91	5	0.000 9	1
5 329.39	5	0.148 3	1
5 025.35	5	0.057 0	1
6 432.78	5	0.280 1	1
6 483.37	4	0.007 9	1
5 316.07	2	0.180 0	1
5 737.25	4	0.079 2	1
4 846.38	5	0.155 3	1
5 559.16	5	0.147 1	1
5 162.35	5	0.071 4	1
4 921.80	4	0.046 6	1
5 136.60	3	0.043 6	1
6 333.46	5	0.233 0	1
5 287.29	4	0.165 2	1
6 474.44	4	0.224 5	1
5 914.53	5	0.086 5	1
7 025.05	3	0.187 8	1
4 716.10	3	0.328 7	1
7 045.00	2	0.493 8	1
4 885.37	5	0.306 5	1
5 072.60	5	0.038 3	1
4 618.32	4	0.089 6	1
3 323.82	4	0.280 3	1
3 717.93	5	0.118 6	1
6 172.03	4	0.660 1	1
1 768.42	6	0.708 3	0
406.94	5	0.769 9	0
2 308.80	5	0.214 0	0
542.24	4	0.765 1	0
707.29	6	0.304 4	0
1 732.63	7	0.689 8	0
665.26	3	0.616 0	0
526.71	7	0.208 3	0
550.96	5	0.046 0	0
398.71	8	0.276 3	0
501.77	4	0.258 5	0
530.29	6	0.056 8	0
1 032.97	5	0.947 9	0
2 540.42	6	0.685 3	0
800.18	6	0.685 0	0
898.09	7	0.433 0	0
846.05	6	0.057 9	0
535.03	8	0.367 6	0
1 308.84	7	0.691 4	0
1 124.92	6	0.140 5	0
1 454.63	8	0.293 1	0
1 160.54	9	0.202 2	0
960.39	4	0.172 5	0
1 546.57	7	0.610 3	0
487.92	6	0.684 5	0
661.14	9	0.355 0	0
1 533.55	9	0.757 8	0
1 330.59	8	0.132 3	0
554.20	6	0.583 5	0
501.95	6	0.094 3	0
1 658.74	7	0.433 9	0
860.95	7	0.481 0	0

序号	样本总数	实际分类(样本数)		鉴别结果(样本数)		正确率/%
序号	样本总数	舰船	海杂波	舰船	海杂波	正确率/%
1	93	93	0	91	2	97.85
2	141	141	0	140	1	99.29
3	88	0	88	0	88	100.00
4	120	0	120	2	118	98.33

序号	样本总数	实际分类(样本数)		鉴别结果(样本数)		正确率/%
序号	样本总数	舰船	海杂波	舰船	海杂波	正确率/%
1	72	72	0	65	7	90.28
2	134	134	0	124	10	92.54
3	101	0	101	11	90	89.11
4	136	0	136	14	122	91.53

[1]	王潇怡, 罗运华, 喻忠军, 孙浩, 王晓蓓. 基于EfficientNet的多通道雷达目标微动特征分类方法[J]. 系统工程与电子技术, 2024, 46(9): 2988-2998.
[2]	王全全, 顾志豪, 吴城坤, 宛汀. 基于HHO-SVM的抗SSDF攻击协作频谱感知方法[J]. 系统工程与电子技术, 2024, 46(6): 2146-2154.
[3]	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.
[4]	刘帅康, 曹伟, 管志强, 杨学岭, 许金鑫. 基于RMDLPP的雷达空中目标分类[J]. 系统工程与电子技术, 2024, 46(4): 1220-1228.
[5]	杨德贵, 许道峰. 基于时频域特征融合的IR-UWB穿墙雷达人体行为识别方法[J]. 系统工程与电子技术, 2024, 46(3): 849-858.
[6]	焦志强, 易侃, 张杰勇, 姚佩阳. 不平衡数据下基于SVM增量学习的指挥信息系统状态监控方法[J]. 系统工程与电子技术, 2024, 46(3): 992-1003.
[7]	张俊玲, 董玫, 陈伯孝. 基于可调Q因子小波变换的海杂波抑制算法[J]. 系统工程与电子技术, 2023, 45(2): 343-351.
[8]	宋波涛, 许广亮. 基于LSTM与1DCNN的导弹轨迹预测方法[J]. 系统工程与电子技术, 2023, 45(2): 504-512.
[9]	李园, 史宪铭, 李亚娟, 赵美. 基于Adaboost的作战目标属性判定方法[J]. 系统工程与电子技术, 2022, 44(4): 1256-1262.
[10]	薛春岭, 曹菲, 孙庆, 秦建强, 冯晓伟. 基于多特征信息融合的海面微弱目标检测[J]. 系统工程与电子技术, 2022, 44(11): 3338-3345.
[11]	朱峰, 蒋倩倩, 林川, 杨啸. 基于支持向量机的典型宽带电磁干扰源识别[J]. 系统工程与电子技术, 2021, 43(9): 2400-2406.
[12]	李昂, 聂党民, 温祥西, 王泽坤, 杨诚修. 基于相依网络和SVM的管制系统运行态势评估[J]. 系统工程与电子技术, 2021, 43(5): 1287-1294.
[13]	陈唯实, 黄毅峰, 陈小龙, 卢贤锋, 张洁. 基于模型转换频率估计的低空目标分类[J]. 系统工程与电子技术, 2021, 43(4): 927-936.
[14]	王坤, 侯树贤, 王力. 基于自适应变异PSO-SVM的APU性能参数预测模型[J]. 系统工程与电子技术, 2021, 43(2): 526-536.
[15]	马愈昭, 王强强, 王瑞松, 熊兴隆. 基于SVD和MPSO-SVM的光纤周界[J]. 系统工程与电子技术, 2020, 42(8): 1652-1661.