Electromagnetic Signal Feature Matching Characterization for Constant False Alarm Detection
-
摘要: 传统恒虚警(Constant False Alarm Rate, CFAR)检测通过统计信号功率参数设定检测门限，其检测性能受限于信噪比，如何挖掘和利用功率参数之外的信号特征，实现更低信噪比的恒虚警检测是该文的研究重点。该文针对高斯白噪声背景下的弱小目标检测，提出了一种基于信号特征匹配的恒虚警检测方法，分析检测单元回波与理想回波信号的深度特征匹配度，以匹配度参数驱动目标检测，通过统计得到关于匹配度参数的恒虚警检测门限。仿真数据与多个频段雷达实测数据处理结果均表明，相比于传统CFAR检测方法及其他机器学习和深度学习方法而言，该文所提方法具有良好恒虚警特性的同时，表现出更佳的检测性能，等效信噪比改善2～5 dB。Abstract:
Objective Small targets such as unmanned aerial vehicles and unmanned vessels, which exhibit small Radar Cross Section (RCS) values and weak echoes, are difficult to detect due to their low observability. Traditional Constant False Alarm Rate (CFAR) detection is typically represented by the Cell-Averaged (CA) CFAR method, in which the detection threshold is determined by the statistical power parameter of the signal. However, its detection performance is constrained by the Signal-to-Noise Ratio (SNR). This study focuses on how to exploit and apply signal features beyond power parameters to achieve CFAR detection under lower SNR conditions. Methods After pulse compression, the envelope of a Linear Frequency Modulation (LFM) signal exhibits sinc characteristics, whereas noise retains its random nature. This difference can be used to distinguish target echoes from non-target signals. On this basis, we propose a constant false alarm detection method based on signal feature matching. First, both the ideal echo signal and the actual echo signal are processed with sliding windows of equal length to generate an ideal sample and a set of test samples. A dual-port fully connected neural network is then constructed to extract the deep feature matching degree between the ideal sample and the test samples. Finally, the constant false alarm threshold is obtained by numerically calculating the deep feature matching parameter from a large number of non-target samples compared with the standard sample. Results and Discussions Several sets of simulation experiments are carried out, and measured radar data from different frequency bands are applied to verify the effectiveness of the proposed method. The simulations first confirm that the method maintains stable constant false alarm characteristics ( Table 1 ). The detection performance is then compared with traditional CA-CFAR detection, machine learning approaches, and other deep learning methods. The results indicate that, relative to CA-CFAR detection, the proposed method achieve 2–5 dB gain in equivalent SNR across different false alarm probabilities (Fig. 4 ). Under mismatched SNR conditions, the method continues to demonstrate robust detection performance with strong generalization capability (Fig. 5 ). In the processing of measured X-band radar data, the proposed method detects targets that CA-CFAR fails to identify, extending the detection range to 740 distance units, compared with 562 distance units for CA-CFAR, corresponding to an improvement of approximately 28.72% in radar detection capability (Fig. 7 ,8 ). In the case of S-band radar data, the proposed method significantly reduces false alarms (Fig. 10 ,11 ).Conclusions This study exploits the difference between target and noise signal envelopes by introducing a feature extraction network that effectively enhances target detection performance. Comparative simulation experiments and the processing of measured radar data across different frequency bands demonstrate the following: (1) the proposed method markedly improves detection performance over traditional CA-CFAR detection, yielding a 2–5 dB gain in equivalent SNR; (2) under mismatched SNR conditions, the method shows strong generalization capability, achieving better detection performance than other deep learning and machine learning approaches; (3) in X-band radar data processing, the method increases detection capability by approximately 28.72%; and (4) in S-band radar data processing, it significantly reduces false alarms. Future work will focus on accelerating the detection process to further improve efficiency. -
表 1 不同滑窗下实际虚警概率及相对误差
滑窗长度 期望虚警概率 10–1 10–2 10–3 10–4 10–5 N=9 1.008×10–1(0.824%) 1.003×10–2(0.293%) 0.998×10–3(0.183%) 0.997×10–4(0.338%) 1.013×10–5(1.351%) N=17 0.972×10–1(2.805%) 0.957×10–2(4.298%) 0.962×10–3(3.824%) 0.967×10–4(3.253%) 0.942×10–5(5.822%) N=25 1.008×10–1(0.767%) 0.985×10–2(1.518%) 0.982×10–3(1.765%) 0.956×10–4(4.369%) 1.041×10–5(4.167%) N=33 1.065×10–1(6.516%) 1.042×10–2(4.195%) 1.017×10–3(1.712%) 0.995×10–4(0.528%) 1.056×10–5(5.634%) N=41 1.119×10–1(11.912%) 1.089×10–2(8.935%) 1.065×10–3(6.533%) 1.036×10–4(3.571%) 1.071×10–5(7.143%) N=49 1.153×10–1(15.339%) 1.139×10–2(13.850%) 1.085×10–3(8.469%) 1.096×10–4(9.601%) 0.996×10–5(0.362%) 
下载: 导出CSV
-
[1] RICHARDS M A, 邢孟道, 王彤, 李真芳, 等译. 雷达信号处理基础[M]. 北京: 电子工业出版社, 2008: 262.RICHARDS M A, XING Mengdao, WANG Tong, LI Zhenfang, et al. translation. Fundamentals of Radar Signal Processing[M]. Beijing: Publishing House of Electronics Industry, 2008: 262. [2] 张梦妮, 王祎鸣, 吴勇剑. 基于改进Mask R-CNN的船载地波雷达目标检测方法[J]. 海洋科学进展, 2025, 43(3): 693–705. doi: 10.12362/j.issn.1671-6647.20231226001.ZHANG Mengni, WANG Yiming, and WU Yongjian. Target detection method of shipborne surface wave radar based on improved mask R-CNN[J]. Advances in Marine Science, 2025, 43(3): 693–705. doi: 10.12362/j.issn.1671-6647.20231226001. [3] 李旭冬, 叶茂, 李涛. 基于卷积神经网络的目标检测研究综述[J]. 计算机应用研究, 2017, 34(10): 2881–2886,2891. doi: 10.3969/j.issn.1001-3695.2017.10.001.LI Xudong, YE Mao, and LI Tao. Review of object detection based on convolutional neural networks[J]. Application Research of Computers, 2017, 34(10): 2881–2886,2891. doi: 10.3969/j.issn.1001-3695.2017.10.001. [4] BHATTACHARYA T K and HAYKIN S. Neural network-based radar detection for an ocean environment[J]. IEEE Transactions on Aerospace and Electronic Systems, 1997, 33(2): 408–420. doi: 10.1109/7.575874. [5] LIU Ningbo, XU Yanan, TIAN Yonghua, et al. Background classification method based on deep learning for intelligent automotive radar target detection[J]. Future Generation Computer Systems, 2019, 94: 524–535. doi: 10.1016/j.future.2018.11.036. [6] 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 Ningyuan, CHEN Xiaolong, GUAN Jian, et al. Detection and classification of maritime target with micro-motion based on CNNs[J]. Journal of Radars, 2018, 7(5): 565–574. doi: 10.12000/JR18077. [7] 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 Ningyuan, CHEN Xiaolong, GUAN Jian, 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. [8] 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): 47–52,57. doi: 10.16592/j.cnki.1004-7859.2019.10.009.SU Ningyuan, CHEN Xiaolong, CHEN Baoxin, et al. Dual-channel convolutional neural networks feature fusion method for radar maritime target intelligent detection[J]. Modern Radar, 2019, 41(10): 47–52,57. doi: 10.16592/j.cnki.1004-7859.2019.10.009. [9] SHI Yanling, GUO Yaxing, YAO Tingting, et al. Sea-surface small floating target recurrence plots FAC classification based on CNN[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 5115713. doi: 10.1109/TGRS.2022.3192986. [10] WANG Jingang and LI Songbin. Maritime radar target detection in sea clutter based on CNN with dual-perspective attention[J]. IEEE Geoscience and Remote Sensing Letters, 2023, 20: 3500405. doi: 10.1109/LGRS.2022.3230443. [11] QU Qizhe, LIU Weijian, WANG Jiaxin, 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. [12] SHI Yanling and CHEN Weisheng. Sea surface target detection using global false alarm controllable adaptive boosting based on correlation features[J]. IEEE Transactions on Geoscience and Remote Sensing, 2023, 61: 5103014. doi: 10.1109/TGRS.2023.3265480. [13] 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 Xiang, WANG Yumiao, CHEN Xingyu, 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. [14] 邱明劼, 张鹏, 汪圣利. 一种基于ResNet的雷达弱小目标检测方法[J]. 无线电工程, 2024, 54(7): 1652–1659. doi: 10.3969/j.issn.1003-3106.2024.07.007.QIU Mingjie, ZHANG Peng, and WANG Shengli. A detection method for radar weak targets based on ResNet[J]. Radio Engineering, 2024, 54(7): 1652–1659. doi: 10.3969/j.issn.1003-3106.2024.07.007. [15] 项厚宏, 马宏伟, 余海军, 等. 自监督特征相似度表征的恒虚警检测方法[J/OL]. https://link.cnki.net/urlid/11.2422.tn.20250414.1152.008, 2025.XIANG Houhong, MA Hongwei, YU Haijun, et al. Self-supervised feature similarity representation for constant false alarm rate detection method[J/OL]. Systems Engineering and Electronics, https://link.cnki.net/urlid/11.2422.tn.20250414.1152.008, 2025. -
图(11) / 表(1)
计量
- 文章访问数: 22
- HTML全文浏览量: 12
- PDF下载量: 4
- 被引次数: 0
下载:
