基于卷积神经网络的雷达目标HRRP分类识别方法
|
摘要
卷积神经网络通过卷积和池化操作提取图像在各个层次上的特征进而对目标进行有效识别,是深度学习网络中应用最广泛的一种。文中围绕一维距离像雷达导引头自动目标识别,开展基于卷积神经网络的目标高分辨距离像分类识别方法研究。首先,基于空中目标一维距离像姿态敏感性仿真生成近似平行交会条件下不同类型目标的高分辨距离像数据集;其次,构建一种一维卷积神经网络结构对目标高分辨距离像进行分类识别;作为比较,针对同类高分辨距离像数据集,分析了主成分分析-支持向量机方法的目标分类识别效果。结果表明:基于卷积神经网络的目标分类识别算法有更好的识别能力,对高分辨距离像的姿态敏感性具有较强的适应性。
Convolutional neural network(CNN) is a deep learning network which has been widely used. CNN has a good performance on target classification and recognition. Features of images can be extracted by CNN through convolution and pooling operations. A radar automatic target recognition algorithm has been discussed in this paper. It is based on high range resoluton profile(HRRP) and CNN. Firstly, HRRPs of several air targets under approximately parallel intersection conditions have been generated to construct the dataset. Then, a CNN has been used to classify and recognize the HRRPs. Finally, the result with another algorithm which is based on principal component analysis and support vector machine are compured, that CNN has a better performance and strong adaptability to the attitude sensitivity of HRRPs.
Convolutional neural network(CNN) is a deep learning network which has been widely used. CNN has a good performance on target classification and recognition. Features of images can be extracted by CNN through convolution and pooling operations. A radar automatic target recognition algorithm has been discussed in this paper. It is based on high range resoluton profile(HRRP) and CNN. Firstly, HRRPs of several air targets under approximately parallel intersection conditions have been generated to construct the dataset. Then, a CNN has been used to classify and recognize the HRRPs. Finally, the result with another algorithm which is based on principal component analysis and support vector machine are compured, that CNN has a better performance and strong adaptability to the attitude sensitivity of HRRPs.
引文
[1] 程嘉远.深度学习在雷达通信目标识别中的应用框架[J].现代雷达,2018,40(8):55-59.CHENG Jiayuan.Application framework of deep leaning in radar communication object recognition[J].Modern Radar,2018,40(8):55-59.
[2] ZHANG R,WEI X Z,LI X.Analysis of the spectra features of speckled HRRP based on the matching score[J].Journal of Electronics & Information Technology,2012,34(4):891-897.
[3] MOLCHANOV P,EGIAZARIAN K,ASTOLA J,et al.Classification of aircraft using micro-Doppler bicoherence-based features[J].IEEE Transactions on Aerospace and Electronic Systems,2014,50(2):1455-1467.
[4] WU J,ZHOU J J,ZHU J H.A radar target recognition method based on wavelet power spectrum and power offset[C]// Second International Asia Conference on Informatics in Control Automation and Robotics.Wuhan:IEEE Press,2010:130-134.
[5] THIAGRAJAN J J,RAMAMURTHY K N,KNEE P,et al.Sparse representation for automatic target classification in SAR images[C]// 2010 4th International Symposium on Communications,Control and Signal Processing.Limassol:IEEE Press,2010:1-4.
[6] HOUSSEINI A E,TOUMI A,KHENCHAF A.Deep learning for target recognition from SAR images[C]// 2017 Seminar on Detection Systems Architectures & Technologies.Algiers:IEEE Press,2017:20-22.
[7] CUI Z Y,DANG S H,CAO Z J ,et al.SAR target recognition in large scene images via region-based convolutional neural networks[J].Remote Sensing,2018,10(5):776-780.
[8] 刘晨,曲长文,周强,等.基于卷积神经网络迁移学习的SAR图像目标分类[J].现代雷达,2018,40(3):38-42.LIU Chen,QU Changwen,ZHOU Qiang,et al.SAR image target classification based on convolutional network transfer learning[J].Modern Radar,2018,40(3):38-42.
[9] 詹武平,郑永煌,王金霞.基于深度神经网络模型的雷达目标识别[J].现代雷达,2018,40(1):16-19.ZHAN Wuping,ZHENG Yonghuang,WANG Jinxia.Radar target recognition based on deep neural network[J].Modern Radar,2018,40(1):16-19.
[10] MCCANN M T,JIN K H,UNSER M.A review of convolutional neural networks for inverse problems in imaging[J].Signal Processing Magazine,2017,34(6):85-95.
[11] LNGKVIST M,KARLSSON L,LOUTFI L.A review of unsupervised feature learning and deep learning for time series modeling[J].Pattern Recognition Letters,2014,42(1):11-24.
[12] LUNDEN J,KOIVUNEN V.Deep learning for HRRP-based target recognition in multistatic radar systems[C]// 2016 IEEE Radar Conference.Philadelphia:IEEE Press,2010:1-6.
[13] SOUIA V M A,SILVA D F,BATISTA G E A P A.Extracting texture features for time series classification[C]// 2014 22nd International Conference on Pattern Recognition.Stockholm:IEEE Press,2014:1425-1430.
[14] SAINATH T N,KINGSBURY B,SAON G,et al.Deep convolution neural networks for large-scale speech tasks[J].Neural Networks,2015,64(14):39-48.
[2] ZHANG R,WEI X Z,LI X.Analysis of the spectra features of speckled HRRP based on the matching score[J].Journal of Electronics & Information Technology,2012,34(4):891-897.
[3] MOLCHANOV P,EGIAZARIAN K,ASTOLA J,et al.Classification of aircraft using micro-Doppler bicoherence-based features[J].IEEE Transactions on Aerospace and Electronic Systems,2014,50(2):1455-1467.
[4] WU J,ZHOU J J,ZHU J H.A radar target recognition method based on wavelet power spectrum and power offset[C]// Second International Asia Conference on Informatics in Control Automation and Robotics.Wuhan:IEEE Press,2010:130-134.
[5] THIAGRAJAN J J,RAMAMURTHY K N,KNEE P,et al.Sparse representation for automatic target classification in SAR images[C]// 2010 4th International Symposium on Communications,Control and Signal Processing.Limassol:IEEE Press,2010:1-4.
[6] HOUSSEINI A E,TOUMI A,KHENCHAF A.Deep learning for target recognition from SAR images[C]// 2017 Seminar on Detection Systems Architectures & Technologies.Algiers:IEEE Press,2017:20-22.
[7] CUI Z Y,DANG S H,CAO Z J ,et al.SAR target recognition in large scene images via region-based convolutional neural networks[J].Remote Sensing,2018,10(5):776-780.
[8] 刘晨,曲长文,周强,等.基于卷积神经网络迁移学习的SAR图像目标分类[J].现代雷达,2018,40(3):38-42.LIU Chen,QU Changwen,ZHOU Qiang,et al.SAR image target classification based on convolutional network transfer learning[J].Modern Radar,2018,40(3):38-42.
[9] 詹武平,郑永煌,王金霞.基于深度神经网络模型的雷达目标识别[J].现代雷达,2018,40(1):16-19.ZHAN Wuping,ZHENG Yonghuang,WANG Jinxia.Radar target recognition based on deep neural network[J].Modern Radar,2018,40(1):16-19.
[10] MCCANN M T,JIN K H,UNSER M.A review of convolutional neural networks for inverse problems in imaging[J].Signal Processing Magazine,2017,34(6):85-95.
[11] LNGKVIST M,KARLSSON L,LOUTFI L.A review of unsupervised feature learning and deep learning for time series modeling[J].Pattern Recognition Letters,2014,42(1):11-24.
[12] LUNDEN J,KOIVUNEN V.Deep learning for HRRP-based target recognition in multistatic radar systems[C]// 2016 IEEE Radar Conference.Philadelphia:IEEE Press,2010:1-6.
[13] SOUIA V M A,SILVA D F,BATISTA G E A P A.Extracting texture features for time series classification[C]// 2014 22nd International Conference on Pattern Recognition.Stockholm:IEEE Press,2014:1425-1430.
[14] SAINATH T N,KINGSBURY B,SAON G,et al.Deep convolution neural networks for large-scale speech tasks[J].Neural Networks,2015,64(14):39-48.