Ground moving target classification based on micro-Doppler signature using novel spectral information features

A novel spectral-based feature set is proposed for ground moving target classification using a battlefield surveillance radar. Precise frequencies and coefficients are extracted from the backscattered radar signal which is used as an information in Automatic Target Recognition (ATR) system to solve the problem of ground moving target classification. The proposed ATR system is realized by combining Gaussian Mixture Model (GMM) with Maximum Likelihood (ML) rule. Experimental signals, realized with ground surveillance radar operating in centimetre range wavelengths, are used to test our ATR system. Numerical evaluation results are presented to assess the performance gain provided by the proposed method.

[1]  Dan Roth,et al.  Constraint Classification: A New Approach to Multiclass Classification , 2002, ALT.

[2]  Weixian Liu,et al.  Radar Micro-Doppler Signature Analysis with HHT , 2010, IEEE Transactions on Aerospace and Electronic Systems.

[3]  Torsten Söderström,et al.  ESPRIT-like estimation of real-valued sinusoidal frequencies , 2004, IEEE Transactions on Signal Processing.

[4]  Andrew R. Barron,et al.  Mixture Density Estimation , 1999, NIPS.

[5]  Victor C. Chen,et al.  Analysis of radar micro-Doppler with time-frequency transform , 2000, Proceedings of the Tenth IEEE Workshop on Statistical Signal and Array Processing (Cat. No.00TH8496).

[6]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[7]  A. Cohen,et al.  Target classification using Gaussian mixture model for ground surveillance Doppler radar , 2005, IEEE International Radar Conference, 2005..

[8]  Douglas A. Reynolds,et al.  Robust text-independent speaker identification using Gaussian mixture speaker models , 1995, IEEE Trans. Speech Audio Process..

[9]  Biing-Hwang Juang,et al.  Fundamentals of speech recognition , 1993, Prentice Hall signal processing series.

[10]  R. O. Schmidt,et al.  Multiple emitter location and signal Parameter estimation , 1986 .

[11]  K. Egiazarian,et al.  Classification of ground moving radar targets by using joint time-frequency analysis , 2012, 2012 IEEE Radar Conference.

[12]  Thomas Kailath,et al.  ESPRIT-estimation of signal parameters via rotational invariance techniques , 1989, IEEE Trans. Acoust. Speech Signal Process..

[13]  A. Cohen,et al.  GMM-based target classification for ground surveillance Doppler radar , 2006, IEEE Transactions on Aerospace and Electronic Systems.

[14]  Milenko S. Andric,et al.  The database of radar echoes from various targets with spectral analysis , 2010, 10th Symposium on Neural Network Applications in Electrical Engineering.

[15]  M. Jahangir,et al.  A robust Doppler classification technique based on hidden Markov models , 2002, RADAR 2002.

[16]  Jaakko Astola,et al.  Classification of ground moving targets using bicepstrum-based features extracted from Micro-Doppler radar signatures , 2013, EURASIP Journal on Advances in Signal Processing.

[17]  Abdesselam Bouzerdoum,et al.  A Human Gait Classification Method Based on Radar Doppler Spectrograms , 2010, EURASIP J. Adv. Signal Process..

[18]  S. Marple.  Computing the discrete-time 'analytic' signal via FFT , 1997 .

[19]  Ian S. Burnett,et al.  Blind speech separation using a joint model of speech production , 2005, IEEE Signal Processing Letters.

[20]  R. Badeau,et al.  Fast adaptive esprit algorithm , 2005, IEEE/SP 13th Workshop on Statistical Signal Processing, 2005.