Radar HRRP target recognition with deep networks

Abstract Feature extraction is the key technique for radar automatic target recognition (RATR) based on high-resolution range profile (HRRP). Traditional feature extraction algorithms usually utilize shallow architectures, which result in the limited capability to characterize HRRP data and restrict the generalization performance for RATR. Aiming at those issues, in this paper deep networks are built up for HRRP target recognition by adopting multi-layered nonlinear networks for feature learning. To learn the stable structure and correlation of targets from unlabeled data, a deep network called Stacked Corrective Autoencoders (SCAE) is further proposed via taking the advantage of the HRRP's properties. As an extension of deep autoencoders, SCAE is stacked by a series of Corrective Autoencoders (CAE) and employs the average profile of each HRRP frame as the correction term. The covariance matrix of each HRRP frame is considered for establishing an effective loss function under the Mahalanobis distance criterion. We use the measured HRRP data to show the effectiveness of our methods. Furthermore, we demonstrate that with the proper optimization procedure, our model is also effective even with a moderately incomplete training set.

[1]  Zheng Bao,et al.  Radar HRRP Statistical Recognition: Parametric Model and Model Selection , 2008, IEEE Transactions on Signal Processing.

[2]  Honglak Lee,et al.  Sparse deep belief net model for visual area V2 , 2007, NIPS.

[3]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[4]  Lan Du,et al.  Radar HRRP target recognition based on K-SVD algorithm , 2011, Proceedings of 2011 IEEE CIE International Conference on Radar.

[5]  Christian Igel,et al.  An Introduction to Restricted Boltzmann Machines , 2012, CIARP.

[6]  Lawrence Carin,et al.  Identification of ground targets from sequential high-range-resolution radar signatures , 2002 .

[7]  Tara N. Sainath,et al.  Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups , 2012, IEEE Signal Processing Magazine.

[8]  Geoffrey E. Hinton,et al.  3D Object Recognition with Deep Belief Nets , 2009, NIPS.

[9]  Pascal Vincent,et al.  Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion , 2010, J. Mach. Learn. Res..

[10]  Zheng Bao,et al.  Noise Robust Radar HRRP Target Recognition Based on Multitask Factor Analysis With Small Training Data Size , 2012, IEEE Transactions on Signal Processing.

[11]  Pascal Vincent,et al.  Representation Learning: A Review and New Perspectives , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Tara N. Sainath,et al.  Deep Neural Networks for Acoustic Modeling in Speech Recognition , 2012 .

[13]  Jaakko Astola,et al.  Classification of aircraft using micro-Doppler bicoherence-based features , 2014, IEEE Transactions on Aerospace and Electronic Systems.

[14]  Feng Zhu,et al.  Nonstationary Hidden Markov Models for Multiaspect Discriminative Feature Extraction From Radar Targets , 2007, IEEE Transactions on Signal Processing.

[15]  Zheng Bao,et al.  Radar automatic target recognition using complex high-resolution range profiles , 2007 .

[16]  Lei Shi,et al.  Radar HRRP Statistical Recognition With Local Factor Analysis by Automatic Bayesian Ying-Yang Harmony Learning , 2011, IEEE Trans. Signal Process..

[17]  B. Zheng Analysis of Three Kinds of Classification Based on Different Absolute Alignment Methods , 2006 .

[18]  A. Zyweck,et al.  Radar target classification of commercial aircraft , 1996, IEEE Transactions on Aerospace and Electronic Systems.

[19]  Hua Yu,et al.  A direct LDA algorithm for high-dimensional data - with application to face recognition , 2001, Pattern Recognit..

[20]  Yoshua Bengio,et al.  Greedy Layer-Wise Training of Deep Networks , 2006, NIPS.

[21]  David B. Dunson,et al.  Deep Learning with Hierarchical Convolutional Factor Analysis , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  Yann LeCun,et al.  What is the best multi-stage architecture for object recognition? , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[23]  Zheng Bao,et al.  Large Margin Feature Weighting Method via Linear Programming , 2009, IEEE Transactions on Knowledge and Data Engineering.

[24]  Hsueh-Jyh Li,et al.  Using range profiles as feature vectors to identify aerospace objects , 1993 .

[25]  Mengdao Xing,et al.  Radar HRRP target recognition based on higher order spectra , 2005, IEEE Transactions on Signal Processing.

[26]  Yoshua. Bengio,et al.  Learning Deep Architectures for AI , 2007, Found. Trends Mach. Learn..

[27]  Michael Elad,et al.  Stable recovery of sparse overcomplete representations in the presence of noise , 2006, IEEE Transactions on Information Theory.

[28]  Z. Bao,et al.  Properties of high-resolution range profiles , 2002 .

[29]  Yoshua Bengio,et al.  Deep Learning of Representations for Unsupervised and Transfer Learning , 2011, ICML Unsupervised and Transfer Learning.

[30]  Zheng Bao,et al.  Bayesian Spatiotemporal Multitask Learning for Radar HRRP Target Recognition , 2011, IEEE Transactions on Signal Processing.

[31]  Zheng Bao,et al.  A new feature vector using selected bispectra for signal classification with application in radar target recognition , 2001, IEEE Trans. Signal Process..

[32]  Geoffrey E. Hinton A Practical Guide to Training Restricted Boltzmann Machines , 2012, Neural Networks: Tricks of the Trade.