Spatial analysis of target signatures

Moving or stationary target Synthetic Aperture Radar (SAR) signatures can be analyzed and used to identify and classify target type against known stored target data base, consisting of full circle raw target data. Public target data base is used as data source, and additionally derived target signature characteristics are generated suitable for target identification. Pose, angle between position and velocity, can be derived in this process and it can be used to reduce search space and hence increase likelihood of Automatic Target Identification (ATR). Our goal in this paper is to define new methodology to analyze target data, using stored signatures as well as real time target signature, and generating variety of spatial statistics and correlations. Besides applications in defense area, there are numerous commercial applications in machine learning, augmented reality, traffic control, and facial recognition.

[1]  R. A. Mitchell,et al.  Robust statistical feature based aircraft identification , 1999 .

[2]  William C. Snyder,et al.  Modeling performance and image collection utility for multiple look ATR , 2004, SPIE Defense + Commercial Sensing.

[3]  Lee C. Potter,et al.  Model-based classification of radar images , 2000, IEEE Trans. Inf. Theory.

[4]  David A. Simon,et al.  Multiple model estimator for a tightly coupled HRR automatic target recognition and MTI tracking system , 1999, Defense, Security, and Sensing.

[5]  Robert L. Williams,et al.  Automatic target recognition of time critical moving targets using 1D high range resolution (HRR) radar , 1999 .

[6]  Erik Blasch,et al.  Robust multi-look HRR ATR investigation through decision-level fusion evaluation , 2008, 2008 11th International Conference on Information Fusion.

[7]  Erik Blasch,et al.  Multilevel feature-based fuzzy fusion for target recognition , 2000, SPIE Defense + Commercial Sensing.

[8]  Roland Jonsson,et al.  Comparison of some HRR-classification algorithms , 2001, SPIE Defense + Commercial Sensing.

[9]  Maria L. Rizzo,et al.  Brownian distance covariance , 2009, 1010.0297.

[10]  Bart Kahler,et al.  Preliminary comparison of high-range resolution signatures of moving and stationary ground vehicles , 2002, SPIE Defense + Commercial Sensing.

[11]  Migdat I. Hodzic,et al.  Pose Estimation Methodology for Target Identification and Tracking , 2015, ICONS 2015.

[12]  A. Leon-Garcia.  Probability, statistics, and random processes for electrical engineering , 2008 .

[13]  Renbiao Wu,et al.  ATR scheme based on 1-D HRR profiles , 2002 .

[14]  Bart Kahler,et al.  An ATR challenge problem using HRR data , 2008, SPIE Defense + Commercial Sensing.