GMM-based target classification for ground surveillance Doppler radar

An automatic target recognition (ATR) algorithm, based on greedy learning of Gaussian mixture model (GMM) is developed. The GMMs were obtained for a wide range of ground surveillance radar targets such as walking person(s), tracked or wheeled vehicles, animals, and clutter. Maximum-likelihood (ML) and majority-voting decision schemes were applied to these models for target classification. The corresponding classifiers were trained and tested using distinct databases of target echoes, recorded by ground surveillance radar. ML and majority-voting classifiers obtained classification rates of 88% and 96%, correspondingly. Both classifiers outperform trained human operators.

[1]  Rama Chellappa,et al.  Noncooperative target classification using hierarchical modeling of high-range resolution radar signatures , 1997, IEEE Trans. Signal Process..

[2]  Ben J. A. Kröse,et al.  Efficient Greedy Learning of Gaussian Mixture Models , 2003, Neural Computation.

[3]  K. M. Ponting,et al.  Robust Doppler classification technique based on hidden Markov models , 2003 .

[4]  Simon Haykin,et al.  Classification of radar clutter using neural networks , 1991, IEEE Trans. Neural Networks.

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

[6]  Ismail Jouny,et al.  Target identification using discriminative learning and feature extraction , 1999, Defense, Security, and Sensing.

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

[8]  Robert Tibshirani,et al.  Classification by Pairwise Coupling , 1997, NIPS.

[9]  Il-Seok Oh,et al.  Binary classification trees for multi-class classification problems , 2003, Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings..

[10]  K. M. Ponting,et al.  Correction to `Robust Doppler classification technique based on hidden Markov models' , 2003 .

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

[12]  Anuj Srivastava,et al.  Asymptotic analysis of pattern-theoretic object recognition , 2000, SPIE Defense + Commercial Sensing.

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

[14]  S. Haykin,et al.  Maximum-entropy spectral analysis of radar clutter , 1982, Proceedings of the IEEE.

[15]  John H. L. Hansen,et al.  Discrete-Time Processing of Speech Signals , 1993 .

[16]  A. G. Stove,et al.  A Doppler-based automatic target classifier for a battlefield surveillance radar , 2002, RADAR 2002.

[17]  Ismail Jouny,et al.  Classification of radar clutter using features extracted from the time-frequency domain , 1997, Defense, Security, and Sensing.

[18]  Nikos A. Vlassis,et al.  A Greedy EM Algorithm for Gaussian Mixture Learning , 2002, Neural Processing Letters.

[19]  S. Haykin,et al.  A statistical radar clutter classifier , 1989, Proceedings of the IEEE National Radar Conference.

[20]  Ismail Jouny.  Radar target identification using genetic algorithms , 1998, Defense, Security, and Sensing.

[21]  M. Skolnik,et al.  Introduction to Radar Systems , 2021, Advances in Adaptive Radar Detection and Range Estimation.

[22]  Tomoyuki Hamamura,et al.  A multiclass classification method based on multiple pairwise classifiers , 2003, Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings..

[23]  Dan Roth,et al.  Constraint Classification for Multiclass Classification and Ranking , 2002, NIPS.

[24]  Douglas A. Reynolds,et al.  A Gaussian mixture modeling approach to text-independent speaker identification , 1992 .