-
摘要:
针对传统雷达信号识别算法在低信噪比下识别准确率低的问题,提出了基于多重同步压缩(MSST)时频变换及方向梯度直方图(HOG)特征提取的雷达辐射源信号识别算法。所提算法在雷达时域信号短时傅里叶变换(STFT)基础上进行多重同步压缩处理获得信号时频分布图,通过HOG算子对信号时频分布图进行HOG特征提取,将提取的HOG特征通过主成分分析法(PCA)进行降维,将降维后的特征参数送入支持向量机(SVM)对雷达信号进行分类与识别。实验结果表明:所提算法具有较低的复杂度,当信噪比为−8 dB时,仿真实验与半实物仿真实验针对9种典型雷达信号的识别准确率达到90%以上。
Abstract:Aiming at the problem of low recognition accuracy of traditional radar signal recognition algorithms under low signal-to-noise ratio, a radar emitter recognition algorithm based on multi-synchrosqueezing transform (MSST) time-frequency transformation and histogram of direction gradient (HOG) feature extraction is proposed. The algorithm performs multiple synchronous compression processing on the basis of the short-time Fourier transform (STFT) of the radar time domain signal to obtain the signal time-frequency distribution image, then uses the HOG operator to extract the HOG feature of the signal time-frequency distribution image. The HOG features are dimensionally reduced by principal component analysis (PCA), and finally the feature parameters after dimension reduction are fed into the support vector machine (SVM) to classify and identify the radar signal. The experimental results show that the algorithm has low complexity, and when the signal-to-noise ratio is −8 dB, the recognition accuracy of the simulation experiments and hardware-in-the-loop simulation experiments for 9 typical radar signals can reach more than 90%.
-
表 1 梯度方向和梯度值
Table 1. Gradient direction and gradient values
梯度方向/(°) 90 150 80 70 10 105 140 30 梯度值 30 68 4 38 36 12 17 8 表 2 算法训练时间
Table 2. Algorithm training time
算法 训练
样本训练时间/s 信噪比
−8 dB信噪比
−6 dB信噪比
−4 dB信噪比
−2 dB信噪比
0 dBAlexNet 3600 867 865 862 861 853 SVM 3600 67 66 61 57 54 表 3 算法识别时间
Table 3. Algorithm recognition time
算法 HOG+SVM LBPV+SVM Holder+SVM 识别时间/s 39 48 20 表 4 训练集和测试集在不同信噪比下的整体识别准确率
Table 4. Overall recognition rate of training set and test set under different SNR
训练集信噪比/dB 测试集信噪比/dB 总体识别准确率/% −14 −6 93.06 2 10 100 −2 −10 90.22 10 2 97.61 −14~10 −14~10 92.02 -
[1] KISHORE T R, RAO K D. Automatic intrapulse modulation classification of advanced LPI radar waveforms[J]. IEEE Transactions on Aerospace and Electronic Systems, 2017, 53(2): 901-914. doi: 10.1109/TAES.2017.2667142 [2] IGLESIAS V, GRAJAL J, ROYER P, et al. Real-time low complexity automatic modulation classifier for pulsed radar signals[J]. IEEE Transactions on Aerospace and Electronic Systems, 2015, 51(1): 108-126. doi: 10.1109/TAES.2014.130183 [3] SCHLEHER D C. LPI radar: Fact or fiction[J]. IEEE Aerospace and Electronic Systems Magazine, 2006, 21(5): 3-6. doi: 10.1109/MAES.2006.1635166 [4] 黄颖坤, 金炜东, 葛鹏, 等. 基于多尺度信息熵的雷达辐射源信号识别[J]. 电子与信息学报, 2019, 41(5): 1084-1091. doi: 10.11999/JEIT180535HUANG Y K, JIN W D, GE P, et al. Radar emitter signal identification based on multi-scale information entropy[J]. Journal of Electronics & Information Technology, 2019, 41(5): 1084-1091(in Chinese). doi: 10.11999/JEIT180535 [5] 徐卓君, 杨雯婷, 杨承志, 等. 雷达脉内调制识别的改进残差神经网络算法[J]. 吉林大学学报(工学版), 2021, 51(4): 1454-1460.XU Z J, YANG W T, YANG C Z, et al. Improved residual neural network algorithm for radar intrapulse modulation recognition[J]. Journal of Jilin University (Engineering Edition), 2021, 51(4): 1454-1460(in Chinese). [6] 刘鲁涛, 戴亮军, 陈涛. 基于频谱复杂度的雷达信号调制方式识别[J]. 哈尔滨工程大学学报, 2018, 39(6): 1081-1086. doi: 10.11990/jheu.201708034LIU L T, DAI L J, CHEN T. Radar signal modulation recognition based on spectrum complexity[J]. Journal of Harbin Engineering University, 2018, 39(6): 1081-1086(in Chinese). doi: 10.11990/jheu.201708034 [7] 谢存祥, 张立民, 钟兆根. 基于时频特征提取和残差神经网络的雷达信号识别[J]. 系统工程与电子技术, 2021, 43(4): 917-926.XIE C X, ZHANG L M, ZHONG Z G. Radar signal recognition based on time-frequency feature extraction and residual neural network[J]. Systems Engineering and Electronics, 2021, 43(4): 917-926(in Chinese). [8] 白航, 赵拥军, 胡德秀, 等. 基于Choi-Williams时频图像特征的雷达辐射源识别[J]. 数据采集与处理, 2012, 27(4): 480-485. doi: 10.3969/j.issn.1004-9037.2012.04.014BAI H, ZHAO Y J, HU D X, et al. Radar emitter recognition based on image feature of Choi-Williams time-frequency distribution[J]. Data Acquisition and Processing, 2012, 27(4): 480-485(in Chinese). doi: 10.3969/j.issn.1004-9037.2012.04.014 [9] OBERLIN T, MEIGNEN S, PERRIER V. The Fourier-based synchrosqueezing transform[C]//2014 IEEE International Conference on Acoustics, Speech and Signal Processing. Piscataway: IEEE Press, 2014: 315-319. [10] 倪雪, 王华力, 徐志军, 等. 基于STFT-SST和深度卷积网络的多相码雷达信号识别[J]. 数据采集与处理, 2020, 35(6): 1090-1096.NI X, WANG H L, XU Z J, et al. Polyphase codes radar signal recognition based on STFT-SST and deep convolutional network[J]. Data Acquisition and Processing, 2020, 35(6): 1090-1096(in Chinese). [11] YU G, WANG Z, ZHAO P. Multisynchrosqueezing transform[J]. IEEE Transactions on Industrial Electronics, 2019, 66(7): 5441-5455. doi: 10.1109/TIE.2018.2868296 [12] LI D X, JIA H Y, YE Y C, et al. High power microwave signal detection based on second order multisynchrosqueezing transform[J]. Journal of Physics:Conference Series, 2020, 1617: 012049. doi: 10.1088/1742-6596/1617/1/012049 [13] 王功明. 雷达信号脉内特征分析与识别关键技术研究[D]. 郑州: 战略支援部队信息工程大学, 2019.WANG G M. Research on key technology of radar signal intra-pulse features analysis and recognition[D]. Zhengzhou: Strategic Support Force Information Engineering University, 2019(in Chinese). [14] 钱红艳. 多重同步压缩变换的提升算法及其在地震信号处理中的应用[D]. 成都: 成都理工大学, 2020.QIAN H Y. Lifting algorithm of multiple synchronous compression transform and its application in seismic signal processing[D]. Chengdu: Chengdu University of Technology, 2020(in Chinese). [15] ATAIE R, ZARANDI A A E, MEHRABANI Y S. An efficient inexact full adder cell design in CNFET technology with high-PSNR for image processing[J]. International Journal of Electronics, 2019, 106(6): 928-944. doi: 10.1080/00207217.2019.1576232 [16] 申彤, 庄建军, 黎文斯, 等. 基于HOG特征提取和支持向量机的东巴文识别[J]. 南京大学学报(自然科学), 2020, 56(6): 870-876.SHEN T, ZHUANG J J, LI W S, et al. Research on recognition of Dongba script by a combination of HOG feature extraction and support vector machine[J]. Journal of Nanjing University (Natural Sciences), 2020, 56(6): 870-876(in Chinese). [17] 孟凡杰, 唐宏, 王义哲, 等. 基于时频图像纹理特征的雷达辐射源信号识别[J]. 弹箭与制导学报, 2017, 37(3): 152-156. doi: 10.15892/j.cnki.djzdxb.2017.03.038MENG F J, TANG H, WANG Y Z, et al. Radar emitter signal recognition based on time-frequency image texture feature[J]. Journal of Projectiles, Rockets, Missiles and Guidance, 2017, 37(3): 152-156(in Chinese). doi: 10.15892/j.cnki.djzdxb.2017.03.038 [18] 郭立民, 陈鑫, 陈涛. 基于AlexNet模型的雷达信号调制类型识别[J]. 吉林大学学报(工学版), 2019, 49(3): 1000-1008.GUO L M, CHEN X, CHEN T. Recognition of radar signal modulation type based on AlexNet model[J]. Journal of Jilin University (Engineering Edition), 2019, 49(3): 1000-1008(in Chinese).