Range Profile Target Recognition Using Sparse Representation Based on Feature Space

doi:10.1007/s12204-017-1879-4

Abstract

Abstract: A novel method is presented to improve the recognition rate of warhead in this paper. Firstly, a tool for electromagnetic calculation, like CST Microwave Studio, is used to simulate the frequency response of the electromagnetic scattering. Secondly, the echo and further the range profile are acquired from the frequency response by further processing. Thirdly, a set of discriminative features is extracted from the range profiles of the target. Fourthly, these features are used to construct a dictionary for the sparse representation classifier. Finally, the sample of the target can be classified by solving the sparsest coefficients. Since the reconstruction result is determined by a linear combination of the training samples, this method has a good robustness for the variable features. By formulating the problem within a feature-based sparse representation framework, the presented method combines the discriminative features of each sample during the sparse recovery process rather than in a postprocessing manner. Moreover, based on the feature representation space rather than a single feature or image pixel, the constructed dictionary exhibits both strong expressive and discriminative powers that can enhance the classification performance of the test sample. A series of test results based on the simulated data demonstrates the effectiveness of our method.

Key words: warhead recognition| range profile| sparse representation| feature dictionary| echo simulation

摘要： A novel method is presented to improve the recognition rate of warhead in this paper. Firstly, a tool for electromagnetic calculation, like CST Microwave Studio, is used to simulate the frequency response of the electromagnetic scattering. Secondly, the echo and further the range profile are acquired from the frequency response by further processing. Thirdly, a set of discriminative features is extracted from the range profiles of the target. Fourthly, these features are used to construct a dictionary for the sparse representation classifier. Finally, the sample of the target can be classified by solving the sparsest coefficients. Since the reconstruction result is determined by a linear combination of the training samples, this method has a good robustness for the variable features. By formulating the problem within a feature-based sparse representation framework, the presented method combines the discriminative features of each sample during the sparse recovery process rather than in a postprocessing manner. Moreover, based on the feature representation space rather than a single feature or image pixel, the constructed dictionary exhibits both strong expressive and discriminative powers that can enhance the classification performance of the test sample. A series of test results based on the simulated data demonstrates the effectiveness of our method.

关键词: warhead recognition| range profile| sparse representation| feature dictionary| echo simulation

CLC Number:

TP 753

L ¨U Wentao1* (吕文涛), WANG Junfeng2 (王军锋), YU Wenxian2 (郁文贤), BAO Xiaomin1 (包晓敏). Range Profile Target Recognition Using Sparse Representation Based on Feature Space[J]. Journal of shanghai Jiaotong University (Science), 2017, 22(5): 615-623.

References 27

[1]	WANG T, WANG X S, CHANG Y L, et al. Estimationof precession parameters and generation of ISARimages of ballistic missile targets [J]. IEEE Transactionson Aerospace and Electronic Systems, 2010,46(4): 1983-1995.
[2]	GAO HW, XIE L G, WEN S L, et al. Micro-Dopplersignature extraction from ballistic target with microotions[J]. IEEE Transactions on Aerospace andElectronic Systems, 2010, 46(4): 1969-1982.
[3]	WANG J F, LIU X Z. Improved global range alignmentfor ISAR [J]. IEEE Transactions on Aerospaceand Electronic Systems, 2007, 43(3): 1070-1074.
[4]	SONG E J, TAHK M J. Three-dimensional midcourseguidance using neural networks for interception of ballistictarget [J]. IEEE Transactions on Aerospace andElectronic Systems, 2002, 38(2): 404-414.
[5]	NELSON D E, STARZYK J A, ENSLEY D D. Iteratedwavelet transformation and signal discrimination forHRR radar target recognition [J]. IEEE Transactionson Systems, Man and Cybernetics —Part A: Systemsand Humans, 2003, 33(1): 52-57.
[6]	DU L, LIU H W, BAO Z, et al. Radar HRRP targetrecognition based on higher-order spectra [J]. IEEETransactions on Signal Processing, 2005, 53(7): 2359-2368.
[7]	LIU J, ZHANG J, ZHAO F. Feature for distinguishingpropeller-driven airplanes from turbine-driven airplanes[J]. IEEE Transactions on Aerospace and ElectronicSystems, 2010, 46(1): 222-229.
[8]	XIE B, WANG J F. Recognition of warhead in ballisticmissile defense [C]//2014 the 7th InternationalCongress on Image and Signal Processing. Dalian:IEEE, 2014: 1110-1114.
[9]	COPSEY K, WEBB A. Bayesian gamma mixturemodel approach to radar target recognition [J]. IEEETransactions on Aerospace and Electronic Systems,2003, 39(4): 1201-1217.
[10]	SHI Y, ZHANG X D. A gabor atom network for signalclassification with application in radar target recognition[J]. IEEE Transactions on Signal Processing,2001, 49(12): 2994-3004.
[11]	LIU J, FANG N, XIE Y J, et al. Radar target classificationusing support vector machine and subspacemethods [J]. IET Radar, Sonar and Navigation, 2015,9(6): 632-640.
[12]	WRIGHT J, YANG A Y, GANESH A, et al. Robustface recognition via sparse representation [J]. IEEETransactions on Pattern Analysis and Machine Intelligence,2009, 31(2): 210-227.
[13]	WANG J Q, LI Y H, CHEN K. Radar high-resolutionrange profile recognition via geodesic weighted sparserepresentation [J]. IET Radar, Sonar and Navigation,2015, 9(1): 75-83.
[14]	FENG B, DU L, SHAO C Y, et al. Radar HRRP recognitionbased on robust dictionary learning with smalltraining data size [C]//2013 IEEE Radar Conference.Ottawa: IEEE, 2013: 110-114.
[15]	DONG G G, KUANG G Y, WANG N, et al. SARtarget recognition via joint sparse representation ofmonogenic signal [J]. IEEE Journal of Selected Topicsin Applied Earth Observations and Remote Sensing,2015, 8(7): 3316-3328.
[16]	AHARON M, ELAD M, BRUCKSTEIN A. K-SVD:An algorithm for designing overcomplete dictionariesfor sparse representation [J]. IEEE Transactions onSignal Processing, 2006, 54(11): 4311-4322.
[17]	XING XW, JI K F, ZOU H X, et al. Ship classificationin terra SAR-X images with feature space based sparserepresentation [J]. IEEE Geoscience and Remote SensingLetters, 2013, 10(6): 1562-1566.
[18]	BARANIUK R G. Compressive sensing [J]. IEEE SignalProcessing Magazine, 2007, 24(4): 118-120.
[19]	MIN L H, FENG C. Compressive sensing reconstructionbased on weighted directional total variation [J].Journal of Shanghai Jiao Tong University (Science),2017, 22(1): 114-120.
[20]	CHEN S S, DONOHO D L, SAUNDERS M A. Atomicdecomposition by basis pursuit [J]. SIAM Journal ofScientific Computing, 1998, 20(1): 33-61.
[21]	KIM S J, KOH K, LUSTIG M, et al. An interior pointmethod for large-scale l1-regularized least squares [J].IEEE Journal of Selected Topics in Signal Processing,2007, 1(4): 606-617.
[22]	FIGUEIREDO M A T, NOWAK R D, WRIGHT S J.Gradient projection for sparse reconstruction: Applicationto compressed sensing and other inverse problems[J]. IEEE Journal of Selected Topics in SignalProcessing, 2007, 1(4): 586-597.
[23]	L¨U W T, WANG J F, YU W X. Simulation of echoesfrom ballistic targets [J]. IEEE Antennas and WirelessPropagation Letters, 2014, 13(1): 1361-1364.
[24]	KOZLOV M, TURNER R. A comparison of an softHFSS and CST microwave studio simulation softwarefor multi-channel coil design and SAR estimation at7T MRI [J]. Piers Online, 2010, 6(4): 395-399.
[25]	OMACHI S, OMACHI M. Fast template matchingwith polynomials [J]. IEEE Transactions on ImageProcessing, 2007, 16(8): 2139-2149.
[26]	DOMENICONI C, GUNOPULOS D, PENG J. Largemargin nearest neighbor classifiers [J]. IEEE Transactionson Neural Networks, 2005, 16(4): 899-909.
[27]	FAN R E, CHEN P H, LIN C J. Working set selectionusing second order information for training supportvector machines [J]. Journal of Machine LearningResearch, 2005, 6(1): 1889-1918.