Intelligent CFAR Detector Based on Support Vector Machine

In this paper, we propose an intelligent constant false alarm rate detector, which uses support vector machine (SVM) techniques to improve the radar detection performance in different background environments. The proposed detector uses the variability index statistic as a feature to train a SVM and recognizes the current operational environment based on the classification results. The proposed detector has the intelligence to select the proper detector threshold adaptive to the current operational environment. This detector provides a low loss performance in homogeneous backgrounds and also performs robustly in nonhomogeneous environments including multiple targets and clutter edges.

[1]  G. Trunk.  Range Resolution of Targets Using Automatic Detectors , 1978, IEEE Transactions on Aerospace and Electronic Systems.

[2]  Budiman P. A. Rohman,et al.  Switching CA/OS CFAR using neural network for radar target detection in non-homogeneous environment , 2015, 2015 International Electronics Symposium (IES).

[3]  Hermann Rohling,et al.  Radar CFAR Thresholding in Clutter and Multiple Target Situations , 1983, IEEE Transactions on Aerospace and Electronic Systems.

[4]  T. Jian,et al.  Adaptive detection of sparsely distributed target in non-Gaussian clutter , 2011 .

[5]  John E. Ball.  Low signal-to-noise ratio radar target detection using Linear Support Vector Machines (L-SVM) , 2014, 2014 IEEE Radar Conference.

[6]  Chang-Joo Kim,et al.  Generalized OS CFAR detector with noncoherent integration , 1993, Signal Process..

[7]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[8]  Saleem A. Kassam,et al.  Analysis of CFAR processors in homogeneous background , 1988 .

[9]  H. M. Finn,et al.  Adaptive detection mode with threshold control as a function of spatially sampled clutter level estimates , 1968 .

[10]  V. Hansen,et al.  Detectability Loss Due to "Greatest Of" Selection in a Cell-Averaging CFAR , 1980, IEEE Transactions on Aerospace and Electronic Systems.

[11]  M. Barkat,et al.  Automatic censoring CFAR detector based on ordered data variability for nonhomogeneous environments , 2005 .

[12]  James A. Ritcey,et al.  Performance of MAX family of order-statistic CFAR detectors , 1991 .

[13]  R. Srinivasan,et al.  Robust radar detection using ensemble CFAR processing , 2000 .

[14]  S. D. Himonas,et al.  Automatic censored CFAR detection for nonhomogeneous environments , 1992 .

[15]  Pramod K. Varshney,et al.  Intelligent CFAR processor based on data variability , 2000, IEEE Trans. Aerosp. Electron. Syst..

[16]  Mohamed Bakry El-Mashade.  Detection analysis of linearly combined order statistic CFAR algorithms in nonhomogeneous background environments , 1998, Signal Process..

[17]  John Rickard,et al.  Adaptive Detection Algorithms for Multiple-Target Situations , 1977, IEEE Transactions on Aerospace and Electronic Systems.

[18]  Xiangwei Meng,et al.  Performance analysis of Nitzberg's clutter map for Weibull distribution , 2010, Digit. Signal Process..

[19]  C. Y. Chong,et al.  MIMO Radar Detection in Non-Gaussian and Heterogeneous Clutter , 2010, IEEE Journal of Selected Topics in Signal Processing.

[20]  D. He,et al.  CFAR intrusion detection method based on support vector machine prediction , 2004, 2004 IEEE International Conference onComputational Intelligence for Measurement Systems and Applications, 2004. CIMSA..

[21]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[22]  X. W. Meng,et al.  Performance Analysis of OS-CFAR with Binary Integration for Weibull Background , 2013, IEEE Transactions on Aerospace and Electronic Systems.