融合卷积特征与判别字典学习的低截获概率雷达信号识别

doi:10.3969/j.issn.1000-1093.2019.09.013

摘要/Abstract

摘要： 针对低截获雷达信号通常采用人工特征选择，且在低信噪比、样本数量少情况下识别率低的问题，提出一种融合雷达信号时频图像的卷积特征与字典学习识别算法。该算法以表征信号调制方式的时频图像为基础，通过时频变换获得信号的二维时频数据，输入到LeNet-5卷积神经网络中。网络通过美国MNIST数据库手写数据集进行预训练，将预训练后网络中的2～6层网络参数迁移到新的LeNet-5中，取出第6卷积层的数据作为提取的卷积特征。使用判别字典学习方法进行识别。仿真结果表明：通过预训练处理能够加快网络的收敛与优化，有效提取到每类信号的卷积特征；与文献［4］、文献［24］、文献［25］、文献［26］中4种算法相比，利用判别字典学习能够在样本少、低信噪比情况下取得较高的识别率。

关键词: 雷达信号, 低截获, 卷积神经网络, 卷积特征, 字典学习, 信号识别

Abstract: The selection of artificial features, low signal-to-noise ratio and small number of samples lead to low recognition rate for low probability of intercepting radar signal. A recognition algorithm with convolution feature and discrimination dictionary learning is proposed. The proposed algorithm is based on the time-frequency image representing a signal modulation type, and a two-dimensional signal is obtained by time-frequency transformation, which is input into LeNet-5. The network is retrained through MNIST data set. The network parameters of 2-6 layers are transferred to a new LeNet-5, and the data from the 6th convolution layer is extracted as convolutional feature. Finally, recognition is ended up by discrimination dictionary learning. Simulated results show that the network goes faster in convergence and optimization through pre-training, and can effectively extract the convolution feature of each kind of signal. Higher recognition rate is obtained through discrimination dictionary learning in the condition of low SNR and small samples compared with other algorithms. Key

Key words: radarsignal, lowprobabilityofintercept, convolutionalneuralnetwork, convolutionalfeature, dictionarylearning, signalrecognition

中图分类号:

TN971⁺.1

呙鹏程，吴礼洋. 融合卷积特征与判别字典学习的低截获概率雷达信号识别[J]. 兵工学报, 2019, 40(9): 1881-1889.

GUO Pengcheng, WU Liyang. LPI Radar Signal Recognition with Convolution Feature and Discrimination Dictionary Learning[J]. Acta Armamentarii, 2019, 40(9): 1881-1889.

参考文献

［1］王星, 呙鹏程, 田元荣, 等.基于BDS-GD的低截获概率雷达信号识别[J].北京航空航天大学学报，2018，44(3):583-592.
WANG X, GUO P C, TIAN Y R, et al．LPI radar signal recognition based on BDS-GD [J]. Journal of Beijing University of Aeronautics and Astronautics,2018,44(3):583-592. (in Chinese)
[2］郭立民，寇韵涵，陈涛，等. 基于栈式稀疏自编码器的低信噪比下低截获概率雷达信号调制类型识别[J]. 电子与信息学报, 2018, 40(4)：875-881.
GUO L M, KOU Y H, CHEN T, et al. Low probability of intercept radar signal recognition based on stacked sparse auto-encoder[J]. Journal of Electronics & Information Technology, 2018, 40(4)： 875-881. (in Chinese)
[3］ ZHANG M, LIU L T, DIAO M, et al. LPI radar waveform recognition based on time-frequency distribution[J].Sensors, 2016, 16(10): 1682-1706.
[4］吴笑天，王星，王志鹏，等. 基于Fisher判别字典学习的辐射源调制特征识别[J]. 兵工学报，2018,39(3): 553-559.
WU X T, WANG X, WANG Z P, et al. Emitter signal modulation feature recognition based on fisher discrimination dictionary learning[J]. Acta Armamentarii, 2018,39(3): 553-559. (in Chinese)
[5］ HINTON G E, SALAKHUTDINOV R R.Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786): 504-507.
[6］ KONG S H, KIM M J, HOANG L M, et al. Automatic LPI radar waveform recognition using CNN[J]. IEEE Access, 2018, 6: 4207-4219.
[7］ MA J, HUANG G M, ZUO W, et al. Robust radar waveform recognition algorithm based on random projections and sparse classification [J].IET Radar, Sonar and Navigation, 2014, 8(4): 290-296.
[8］王磊, 周乐囡, 姬红兵, 等. 一种面向信号分类的匹配追踪新方法[J]. 电子与信息学报, 2014, 36(6):1299-1306.
WANG L, ZHOU L N, JI H B, et al. A new matching pursuit algorithm for signal classification[J]. Journal of Electronics and Information Technology, 2014, 36(6): 1299-1306. (in Chinese)
[9］朱甦, 薄煜明, 何亮. 基于冗余字典的多特征压缩感知目标跟踪算法[J].兵工学报, 2017, 38(6): 1140-1146.
ZHU S, BO Y M, HE L. Multi-feature compressive sensing target tracking algorithm based on redundant dictionary [J]. Acta Armamentarii, 2017, 38(6): 1140-1146.(in Chinese)

[10］王伟, 韩纪庆, 郑铁然, 等.基于Fisher判别字典学习的说话人识别[J].电子与信息学报, 2016, 38(2): 367-372.
WANG W, HAN J Q, ZHENG T R, et al. Speaker recognition based on fisher discrimination dictionary learning[J]. Journal of Electronics and Information Technology, 2016, 38(2): 367-372. (in Chinese)
[11］ YANG M, ZHANG L, FENG X C, et al. Sparse representation based fisher discrimination dictionary learning for image classification[J]. International Journal of Computer Vision, 2014, 109(3): 209-232.
[12］ LECUN Y, BENGIO Y, HINTON G E. Deep learning[J]. Nature, 2015, 512(7553):436-444.
[13］ LECUN C Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.
[14］李勇，林小竹，蒋梦莹. 基于跨连接LeNet-5网络的面部表情识别[J].自动化学报, 2018, 44(1): 176-182.
LI Y, LIN X Z, JIANG M Y. Facial expression recognition with cross-connect LeNet-5 network[J］.Acta Automatica Sinica, 2018, 44(1): 176-182.(in Chinese)
[15］ LIN S H, CAI L, LIN X M, et al. Masked face detection via a modified LeNet[J]. Neurocomputing, 2016,218：197-202.
[16］李宝奇，贺昱曜，陈立柱. 光照不变特征提取新方法及其在目标识别中的应用[J].电子学报, 2018, 46(4): 895-902.
LI B Q, HE Y Y, CHEN L Z. A new method for extracting illumination invariant features and its application in target recognition[J]. Acta Electronica Sinica, 2018, 46(4): 895-902.(in Chinese)
[17］刘琼, 李宗贤, 孙富春, 等. 基于深度信念卷积神经网络的图像识别与分类[J/OL].清华大学学报(自然科学版)，2018(2018-05-14)[2018-07-01].http:∥kns. cnki. net/ kcms/detail/11.2223.N.20180511.1520.001.html.
LIU Q, LI Z X, SUN F C, et al. Image recognition and classification by deep belief-convolutional neural networks[J/OL]. Journal of Tsinghua University (Science and Technology), 2018(2018-05-14) [2018-07-01].http:∥kns.cnki.net/kcms/detail/11.2223.N.20180511.1520.001.html. (in Chinese)
[18］葛芸，江顺亮，叶发茂，等. 基于ImageNet预训练卷积神经网络的遥感图像检索[J]. 武汉大学学报（信息科学版），2018,43(1): 67-73.
GE Y, JIANG S L, YE F M, et al. Remote sensing image retrieval using pre-trained convolutional neural networks based on imageNet[J]. Geomatics and Information Science of Wuhan University, 2018,43(1): 67-73. (in Chinese)
[19］ DONAHUE J, JIA Y, VINYALS O, et al. DeCAF: a deep convolutional activation feature for generic visual recognition[C]∥Proceedings of the 31st International Conference on Machine Learning. Beijing, China: International Machine Learning Society, 2014: 647-655.
[20］ OQUAB M, BOTTOU L, LAPTEV I, et al. Learning and transferring mid-level image representation using convolution neural networks[C]∥ Proceedings of the 27th IEEE Conference on Computer Vision and Pattern Recognition. Columbus, US: IEEE, 2014: 1717-1724.
[21］ GU S H, ZHANG L, ZUO W M, et al. Projective dictionary pair learning for pattern classification[M]∥ Advances in Neural Information Processing Systems. Cambridge, MA, US：MIT Press, 2014: 793-801.
[22］曾凌子, 尹东, 张荣, 等. 基于Fisher准则字典学习的压缩感知人脸识别算法[J].模式识别与人工智能, 2014, 27(4): 294-299.
ZENG L Z, YIN D, ZHANG R, et al. Face recognition via compressive sensing based on fisher discrimination dictionary learning[J]. Pattern Recognition and Artificial Intelligence, 2014, 27(4): 294-299. (in Chinese)
[23］ FLANDRIN P, BORGNAT P. Time-frequency energy distribution meet compressed sensing[J]. IEEE Transactions on Signal Processing, 2010, 58(6): 2974-2982.
[24］王星, 周一鹏, 周东青, 等. 基于深度置信网络和双谱对角切片的低截获概率雷达信号识别[J]. 电子与信息学报, 2016，38(11): 2972-2976.
WANG X, ZHOU Y P, ZHOU D Q, et al. Research on low probability of intercept radar signal recognition using deep belief network and bispectra diagonal slice[J]. Journal of Electronics & Information Technology, 2016，38(11): 2972-2976. (in Chinese)
[25］周志文，黄高明，高俊. 基于压缩协作表示的辐射源识别算法[J].航空学报，2016，37(7): 2251-2258.
ZHOU Z W, HUANG G M, GAO J. Emitter recognition algorithm based on compressively collaborative representation[J]. Acta Aeronautica et Astronautica Sinica, 2016，37(7): 2251-2258. (in Chinese)
[26］ XIE J S. Robust intra-pulse modulation recognition via sparse representation[C]∥Proceedings of 2016 CIE International Conference on Radar.Guangzhou, China: Chinese Institute of Elecrtonics, 2017:1-4.

第40卷
第9期2019 年9月兵工学报ACTA
ARMAMENTARIIVol.40No.9Sep.2019

[1]	袁航，罗迎，李开明，陈怡君，张群. 基于涡旋电磁波雷达的人体目标步态精细识别[J]. 兵工学报, 2022, 43(5): 1167-1174.
[2]	普运伟，刘涛涛，郭江，吴海潇. 基于卷积神经网络和模糊函数主脊坐标变换的雷达辐射源信号识别[J]. 兵工学报, 2021, 42(8): 1680-1689.
[3]	马月红，孔梦瑶. 基于改进快速区域卷积网络的目标检测轻量化算法[J]. 兵工学报, 2021, 42(12): 2664-2674.
[4]	戴文君，常天庆，褚凯轩，张雷，郭理彬. 基于时空卷积特征记忆模型的坦克火控系统视频目标检测方法[J]. 兵工学报, 2020, 41(9): 1708-1718.
[5]	张宏鹏，黄长强，唐上钦，轩永波. 基于卷积神经网络的无人作战飞机飞行轨迹实时预测[J]. 兵工学报, 2020, 41(9): 1894-1903.
[6]	刘秋，孙晋伟，张华, 胡煦，顾亮. 基于卷积神经网络的路面识别及半主动悬架控制[J]. 兵工学报, 2020, 41(8): 1483-1493.
[7]	李东瑾，杨瑞娟，董睿杰. 基于联合投影字典学习的辐射源调制识别[J]. 兵工学报, 2020, 41(7): 1464-1472.
[8]	李东瑾，杨瑞娟，李晓柏，朱晟坤，费太勇. 基于栈式降维与字典学习的辐射源调制识别[J]. 兵工学报, 2020, 41(10): 2023-2032.
[9]	吴春志，冯辅周，吴守军，陈汤，江鹏程. 一种有效的不均衡样本生成方法及其在行星变速箱故障诊断中的应用[J]. 兵工学报, 2019, 40(7): 1349-1357.
[10]	梁杰，李磊，任君，齐航，周红丽. 基于深度学习的红外图像遮挡干扰检测方法[J]. 兵工学报, 2019, 40(7): 1401-1410.
[11]	张玉燕，李永保，温银堂，张芝威. 基于Faster R-卷积神经网络的金属点阵结构缺陷识别方法[J]. 兵工学报, 2019, 40(11): 2329-2335.
[12]	吴笑天，王星，王志鹏，周一鹏，陈游. 基于Fisher判别字典学习的辐射源调制特征识别[J]. 兵工学报, 2018, 39(3): 553-559.
[13]	田春瑾，普运伟，郭媛蒲，时羽. 基于图形轮廓的雷达信号模糊函数主脊切面特征提取方法[J]. 兵工学报, 2018, 39(11): 2280-2288.
[14]	孙皓泽，常天庆，王全东，孔德鹏，戴文君. 一种基于分层多尺度卷积特征提取的坦克装甲目标图像检测方法[J]. 兵工学报, 2017, 38(9): 1681-1691.
[15]	王红卫, 范翔宇，陈游，杨远志. 基于循环平稳度准则的多路雷达信号识别算法[J]. 兵工学报, 2016, 37(4): 661-669.