Probabilistic SVM for open set automatic target recognition on high range resolution radar data

The Eigen-Template (ET) based closed-set feature extraction approach is extended to an open-set HRR-ATR framework to develop an Open Set Probabilistic Support Vector Machine (OSP-SVM) classifier. The proposed ET-OSP-SVM is shown to perform open set ATR on HRR data with 80% PCC for a 4-class MSTAR dataset.

[1]  Brian D. Rigling,et al.  Open set recognition for automatic target classification with rejection , 2016, IEEE Transactions on Aerospace and Electronic Systems.

[2]  John Platt,et al.  Probabilistic Outputs for Support vector Machines and Comparisons to Regularized Likelihood Methods , 1999 .

[3]  V. Vapnik.  Estimation of Dependences Based on Empirical Data , 2006 .

[4]  Zheng Bao,et al.  Radar target recognition based on peak location of HRR profile and HMMs classifiers , 2002, RADAR 2002.

[5]  Arnab K. Shaw,et al.  Improved automatic target recognition using singular value decomposition , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[6]  Anderson Rocha,et al.  Toward Open Set Recognition , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Brian D. Rigling,et al.  Ladar ATR via probabilistic open set techniques , 2014, Defense + Security Symposium.

[8]  Stanley C. Ahalt,et al.  Kernel-based discriminant feature extraction using a representative dataset , 2002, SPIE Defense + Commercial Sensing.

[9]  B. Ripley,et al.  Pattern Recognition , 1968, Nature.

[10]  Matthew Scherreik,et al.  A Probabilistic Technique For Open Set Recognition Using Support Vector Machines , 2014 .

[11]  Janusz A. Starzyk,et al.  High range resolution radar target classification: a rough set approach , 2001 .

[12]  Arnab K. Shaw,et al.  Automatic target recognition using Eigen templates , 1998, Defense, Security, and Sensing.

[13]  Junshui Ma.  Feature study for high-range-resolution based automatic target recognition : analysis and extraction / , 2001 .

[14]  M. Brookes,et al.  HRR Automatic Target Recognition from Superresolution Scattering Center Features , 2009, IEEE Transactions on Aerospace and Electronic Systems.

[15]  Andreas Christmann,et al.  Support vector machines , 2008, Data Mining and Knowledge Discovery Handbook.

[16]  Brian D. Rigling,et al.  Multi-class open set recognition for SAR imagery , 2016, SPIE Defense + Security.

[17]  Atindra Mitra,et al.  Improved HRR-ATR using hybridization of HMM and eigen-template-matched filtering , 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

[18]  Brian D. Rigling,et al.  An evaluation of open set recognition for FLIR images , 2015, Defense + Security Symposium.

[19]  Robert L. Williams,et al.  1D HRR data analysis and ATR assessment , 1998, Defense, Security, and Sensing.

[20]  Zheng Bao,et al.  PCA and kernel PCA for radar high range resolution profiles recognition , 2005, IEEE International Radar Conference, 2005..

[21]  Michael A. Temple,et al.  High range resolution (HRR) improvement using synthetic HRR processing and stepped-frequency polyphase coding , 2004 .

[22]  Robert L. Williams,et al.  HRR ATR using eigen templates with noisy observations in unknown target scenario , 2000, SPIE Defense + Commercial Sensing.

[23]  Qun Zhao,et al.  Support vector machines for SAR automatic target recognition , 2001 .

[24]  Arnab K. Shaw,et al.  Robust HRR radar target identification by hybridization of HMM and eigen-template-based matched filtering , 2003, SPIE Defense + Commercial Sensing.

[25]  Robert Williams,et al.  Eigen-Template-Based HRR-ATR with Multi-Look and Time-Recursion , 2013, IEEE Transactions on Aerospace and Electronic Systems.

[26]  Junshui Ma,et al.  Using support vector machines as HRR signature classifiers , 2001, SPIE Defense + Commercial Sensing.