自监督特征相似度表征的恒虚警检测方法

doi:10.12305/j.issn.1001-506X.2025.12.02

系统工程与电子技术 ›› 2025, Vol. 47 ›› Issue (12): 4012-4023.doi: 10.12305/j.issn.1001-506X.2025.12.02

• 电子技术 • 上一篇

自监督特征相似度表征的恒虚警检测方法

项厚宏¹^,*, 马宏伟², 余海军¹, 陈毓锋³, 王凤玉⁴, 曾小路⁵

1. 合肥工业大学计算机与信息学院，安徽合肥 230009
2. 北京无线电测量研究所北京 100854
3. 西安电子科技大学杭州研究院，浙江杭州 311200
4. 北京邮电大学人工智能学院北京 100876
5. 北京理工大学信息与电子学院，北京 100081

收稿日期:2024-11-13 修回日期:2025-02-19 出版日期:2025-04-14 发布日期:2025-04-14
通讯作者: 项厚宏
作者简介:马宏伟（1985—），男，高级工程师，硕士，主要研究方向为雷达系统设计、雷达信号处理
余海军（2004—），男，主要研究方向为智能雷达信号处理
陈毓锋（1994—），男，副研究员，博士，主要研究方向为雷达通信一体化、分布式波形设计、杂波抑制
王凤玉（1992—），女，讲师，博士，主要研究方向为智能信号处理、无线人工智能
曾小路（1991—），男，副研究员，博士，主要研究方向智能无线感知与物联网、复杂环境目标探测与感知
基金资助:
国家自然科学基金（62201189）；安徽省重点研究与开发计划（2023z04020018）；中央高校基本科研业务费专项资金（JZ2024HGTB0228）；雷达信号处理全国重点实验室基金；西安电子科技大学杭州研究院院士工作站基金资助课题

Constant false alarm rate detection method for self-supervised feature similarity representation

Houhong XIANG¹^,*, Hongwei MA², Haijun YU¹, Yufeng CHEN³, Fengyu WANG⁴, Xiaolu ZENG⁵

1. School of Computer and Information，Hefei University of Technology，Hefei 230009，China
2. Beijing Institute of Radio Measurement，Beijing 100854，China
3. Hangzhou Institute of Technology，Xidian University，Hangzhou 311200，China
4. School of Artificial Intelligence，Beijing University of Posts and Telecommunications，Beijing 100876，China
5. School of Information and Electronics，Beijing Institute of Technology，Beijing 100081，China

Received:2024-11-13 Revised:2025-02-19 Online:2025-04-14 Published:2025-04-14
Contact: Houhong XIANG

摘要/Abstract

摘要：

对于弱小目标检测问题，基于功率参数特征的恒虚警率（constant false-alarm rate，CFAR）算法的检测性能受限于目标回波信号的信噪比（signal-to-noise ratio，SNR），如何挖掘功率参数以外更为丰富的特征并表征目标，实现更远距离的弱小目标检测是研究重点。对此，提出一种自监督特征相似度表征的CFAR检测方法。构建一个双端口深度网络特征提取模型，充分挖掘片段化的信号及其自身旋转信号的特征并以相似度参数表征。通过最大化目标空间和无目标空间的相似度参数空间距离，得到最优的特征提取与参数表征模型。最后，通过数值统计计算CFAR条件下的相似度参数检测门限。仿真数据和多种频段的雷达实测数据处理结果表明，在CFAR要求下，所提方法较CFAR检测算法和多种大数据处理算法而言，对未知回波信号参数和未知背景噪声分布特征具有较高的泛化性，其等效SNR改善了3 dB，具有更高的检测性能。

关键词: 弱小目标检测, 恒虚警率检测, 相似性表征, 雷达信号处理

Abstract:

For the problem of weak target detection, the detection performance of the constant false alarm rate （CFAR） algorithm based on power parameter features is limited by the signal-to-noise ratio （SNR） of the target echo signal. How to mine richer features beyond power parameters to characterize the target and achieve weak target detection at longer distances is the focus. In regard to this, a CFAR detection method based on self-supervised feature similarity representation is proposed. A dual-port deep network feature extraction model is constructed to fully mine the features of fragmented signals and their own rotated signals and represent them with similarity parameters. By maximizing the spatial distance of similarity parameters between the target space and the target-free space, the optimal feature extraction and parameter representation model is obtained. Finally, the similarity parameter detection threshold under the CFAR condition is calculated through numerical statistics. The results of processing simulation data and radar measured data in multiple frequency bands show that, with the requirement of CFAR, compared to the CFAR detection algorithm and various big data processing algorithms, the proposed method has higher generalization ability to unknown echo signal parameters and unknown background noise distribution characteristics, with an equivalent SNR improvement of 3 dB, has higher detection performance.

Key words: weak target detection, constant false alarm rate （CFAR） detection, similarity representation, radar signal processing

中图分类号:

TN 958

项厚宏, 马宏伟, 余海军, 陈毓锋, 王凤玉, 曾小路. 自监督特征相似度表征的恒虚警检测方法[J]. 系统工程与电子技术, 2025, 47(12): 4012-4023.

Houhong XIANG, Hongwei MA, Haijun YU, Yufeng CHEN, Fengyu WANG, Xiaolu ZENG. Constant false alarm rate detection method for self-supervised feature similarity representation[J]. Systems Engineering and Electronics, 2025, 47(12): 4012-4023.

图/表 13

图1

图2

表1

图3

图4

图5

图6

图7

表2

图8

图9

表3

图10

参考文献 30

1	马越, 缪晨, 张若愚, 等. “低慢小”无人机雷达探测研究与展望[J]. 国防科技, 2023, 44 (5): 60- 66. doi: 10.13943/j.issn1671-4547.2023.05.08
	MA Y, MIAO C, ZHANG R Y, et al. Current status and future prospects of research on radar detection of “low, slow and small” drones[J]. National Defense Technology, 2023, 44 (5): 60- 66. doi: 10.13943/j.issn1671-4547.2023.05.08
2	胥凤驰, 王伟, 李哲, 等. 水面无人艇系统的设计实现与未来展望[J]. 舰船科学技术, 2019, 41 (12): 39- 43. doi: 10.3404/j.issn.1672-7649.2019.12.009
	XU F C, WANG W, LI Z, et al. Design and realization of unmanned surface vessel system and its future prospects[J]. Ship Science and Technology, 2019, 41 (12): 39- 43. doi: 10.3404/j.issn.1672-7649.2019.12.009
3	GINI F, GRECO M. Texture modelling estimation and validation using measured sea clutter data[J]. IEE Proceedings-Radar Sonar and Navigation, 2002, 149 (3): 115- 124. doi: 10.1049/ip-rsn:20020272
4	CARRERA E V, LARA F, ORTIZ M, et al. Target detection using radar processors based on machine learning[C]//Proc. of the Technical and Scientific Conference of the Andean Council of the IEEE, 2020.
5	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 & Electronic Systems, 2014, 50(2): 1416−1430.
6	LI Y Z, XIE P C, TANG Z S, et al. SVM-based sea-surface small target detection: a false-alarm-rate-controllable approach[J]. IEEE Geoscience and Remote Sensing Letters, 2019, 16 (8): 1225- 1229. doi: 10.1109/LGRS.2019.2894385
7	郭子薰, 水鹏朗, 白晓惠, 等. 海杂波中基于可控虚警K近邻的海面小目标检测[J]. 雷达学报, 2020, 9 (4): 654- 663. doi: 10.12000/JR20055
	GUO Z X, SHUI P L, BAI X H, et al. Sea-surface small target detection based on KNN with controlled false alarm rate in sea clutter[J]. Journal of Radars, 2020, 9 (4): 654- 663. doi: 10.12000/JR20055
8	XU S W, ZHU J A, 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, 2020, 14, 704- 715.
9	GUO Z X, SHUI P L. Anomaly based sea-surface small target detection using K-nearest neighbor classification[J]. IEEE Trans. on Aerospace and Electronic Systems, 2020, 56 (6): 4947- 4964. doi: 10.1109/TAES.2020.3011868
10	陈小龙, 饶桂林, 关键, 等. 被动雷达低慢小探测数据集（LSS-PR-1.0）及多域特征提取和分析方法[J]. 雷达学报, 2025, 14 (2): 249- 268. doi: 10.12000/JR24145
	CHEN X L, RAO G L, GUAN J, et al. Passive radar low slow small detection dataset （LSS-PR-1.0） and multi-domain feature extraction and analysis methods[J]. Journal of Radars, 2025, 14 (2): 249- 268. doi: 10.12000/JR24145
11	XU Y Y, JIN L. Sea-surface floating small target detection based on SVM and multidimensional features[C]//Proc. of the IEEE International Conference on Information Technology, Big Data and Artificial Intelligence, 2020: 453−457.
12	CHANG J Y, FU X J, ZHAO C X, et al. Distributed radar target detection based on RF-SSA in non-Gaussian noise[J]. Electronics, 2022, 11 (15): 2319. doi: 10.3390/electronics11152319
13	BHATTACHARYA T K, HAYKIN S. Neural network-based radar detection for an ocean environment[J]. IEEE Trans. on Aerospace and Electronic Systems, 1997, 33 (2): 408- 420. doi: 10.1109/7.575874
14	PERDOCH J, GAZOVOVA S, PACEK M. An improved radar clutter suppression by simple neural network[J]. IET Radar, Sonar & Navigation, 2024, 18(2): 308−326.
15	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. doi: 10.12000/JR18077
	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 Radar, 2018, 7 (5): 565- 574. doi: 10.12000/JR18077
16	苏宁远, 陈小龙, 关键, 等. 基于深度学习的海上目标一维序列信号目标检测方法[J]. 信号处理, 2020, 36 (12): 1987- 1997. doi: 10.16798/j.issn.1003-0530.2020.12.004
	SU N Y, CHEN X L, GUAN J, et al. One-dimensional sequence signal detection method for marine target based on deep learning[J]. Journal of Signal Processing, 2020, 36 (12): 1987- 1997. doi: 10.16798/j.issn.1003-0530.2020.12.004
17	苏宁远, 陈小龙, 陈宝欣, 等. 雷达海上目标双通道卷积神经网络特征融合智能检测方法[J]. 现代雷达, 2019, 41 (10): 47- 52. doi: 10.16592/j.cnki.1004-7859.2019.10.009
	SU N Y, CHEN X L, CHEN B X, et al. Dual-channel convolutional neural networks feature fusion method for radar maritime target intelligent detection[J]. Modern Radar, 2019, 41 (10): 47- 52. doi: 10.16592/j.cnki.1004-7859.2019.10.009
18	CHEN X L, SU N Y, HUANG Y, et al. False-alarm-controllable radar detection for marine target based on multi features fusion via CNNs[J]. IEEE Sensors Journal, 2021, 21 (7): 9099- 9111. doi: 10.1109/JSEN.2021.3054744
19	SHI Y L, GUO Y X, YAO T T, et al. Sea-surface small floating target recurrence plots FAC classification based on CNN[J]. IEEE Trans. on Geoscience and Remote Sensing, 2022, 60, 5115713.
20	WANG J G, LI S B. Maritime radar target detection in sea clutter based on CNN with dual-perspective attention[J]. IEEE Geoscience and Remote Sensing Letters, 2022, 20, 3500405.
21	QU Q Z, LIU W J, WANG J X, et al. Enhanced CNN-based small target detection in sea clutter with controllable false alarm[J]. IEEE Sensors Journal, 2023, 23 (9): 10193- 10205. doi: 10.1109/JSEN.2023.3259953
22	LIANG S Y, CHEN R, DUAN G, et al. Deep learning-based lightweight radar target detection method[J]. Journal of Real-Time Image Processing, 2023, 20 (4): 61- 71. doi: 10.1007/s11554-023-01316-5
23	YAVUZ F. Radar target detection with CNN[C]//Proc. of the 29th European Signal Processing Conference, 2021: 1581−1585.
24	CHEN J, DU L, GUO G B, et al. Target-attentional CNN for radar automatic target recognition with HRRP[J]. Signal Processing, 2022, 196, 108497. doi: 10.1016/j.sigpro.2022.108497
25	WANG L, TANG J, LIAO Q M. A study on radar target detection based on deep neural networks[J]. IEEE Sensors Letters, 2019, 3 (3): 7000504.
26	SHI Y L, CHEN W S. Sea surface target detection using global false alarm controllable adaptive boosting base on correlation features[J]. IEEE Trans. on Geoscience and Remote Sensing, 2023, 61, 5103014.
27	WANG J G, LI S B. SALA-LSTM: a novel high-precision maritime radar target detection method based on deep learning[J]. Scientific Reports, 2023, 13 (1): 12125- 12139. doi: 10.1038/s41598-023-39348-3
28	BAIRD Z, MCDONALD M K, RAJAN S, et al. A CNN-LSTM network for augmenting target detection in real maritime wide area surveillance radar data[J]. IEEE Access, 2020, 8, 179281- 179294. doi: 10.1109/ACCESS.2020.3025144
29	赵迪, 行鸿彦, 王海峰, 等. 基于SAE-GA-XGBoost算法的海面小目标检测[J]. 雷达科学与技术, 2023, 21 (1): 88- 96. doi: 10.3969/j.issn.1672-2337.2023.01.011
	ZHAO D, XING H Y, WANG H F, et al. Sea-surface small target detection based on SAE-GA-XGBoost algorithm[J]. Radar Science and Technology, 2023, 21 (1): 88- 96. doi: 10.3969/j.issn.1672-2337.2023.01.011
30	汪翔, 汪育苗, 陈星宇, 等. 基于深度学习的多特征融合海面目标检测方法[J]. 雷达学报, 2024, 13 (3): 554- 564. doi: 10.12000/JR23105
	WANG X, WANG Y M, CHEN X Y, et al. Deep learning-based marine target detection method with multiple feature fusion[J]. Journal of Radars, 2024, 13 (3): 554- 564. doi: 10.12000/JR23105

窗长l₀	p_fa
窗长l₀	10⁻¹	10⁻²	10⁻³	10⁻⁴	10⁻⁵	10⁻⁶
9	90.79	15.64	0.45	0.07	0.02	0.01
17	188.70	66.19	27.61	10.92	0.46	0.06
25	270.96	84.79	26.06	8.13	1.95	0.11
33	259.99	82.76	25.64	7.30	2.17	0.08

虚警概率p_fa	检测门限
10⁻¹	55.24
10⁻²	19.94
10⁻³	6.26
10⁻⁴	1.26

虚警概率p_fa	检测门限
10⁻¹	50.17
10⁻²	17.02
10⁻³	7.15
10⁻⁴	3.85

[1]	刘恒燕, 宋杰, 熊伟, 梁晓军. 大入射余角CFAR检测器[J]. 系统工程与电子技术, 2019, 41(6): 1218-1223.
[2]	陆福星, 李夜金, 陈忻, 陈桂林, 饶鹏. 基于Top-hat变换的PM模型弱小目标检测[J]. 系统工程与电子技术, 2018, 40(7): 1417-1422.
[3]	赵文静, 金明录, 刘文龙. 海杂波环境下改进的中值矩阵检测方法[J]. 系统工程与电子技术, 2018, 40(10): 2173-2179.
[4]	陈炳文，王文伟，秦前清. 基于Fuzzy-ART神经网络的红外弱小目标检测[J]. Journal of Systems Engineering and Electronics, 2012, 34(5): 857-863.
[5]	罗小云，李明，左磊，李响. 基于动态规划的雷达微弱目标检测[J]. Journal of Systems Engineering and Electronics, 2011, 33(7): 1491-1496.
[6]	王鑫, 唐振民. 改进的分形算法在弱小目标检测中的应用[J]. Journal of Systems Engineering and Electronics, 2009, 31(9): 2071-2075.
[7]	吴一全, 吴文怡, 罗子娟. 基于最小一乘和遗传算法的红外弱小目标检测[J]. Journal of Systems Engineering and Electronics, 2009, 31(3): 575-578.
[8]	陈尚锋, 肖山竹, 卢焕章. 图像序列弱小目标能量积累检测研究[J]. Journal of Systems Engineering and Electronics, 2009, 31(2): 288-291.

自监督特征相似度表征的恒虚警检测方法

Constant false alarm rate detection method for self-supervised feature similarity representation

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 13

参考文献 30

相关文章 8

编辑推荐

Metrics

本文评价