Classifying sets of attributed scattering centers using a hash coded database

We present a fast, scalable method to simultaneously register and classify vehicles in circular synthetic aperture radar imagery. The method is robust to clutter, occlusions, and partial matches. Images are represented as a set of attributed scattering centers that are mapped to local sets, which are invariant to rigid transformations. Similarity between local sets is measured using a method called pyramid match hashing, which applies a pyramid match kernel to compare sets and a Hamming distance to compare hash codes generated from those sets. By preprocessing a database into a Hamming space, we are able to quickly find the nearest neighbor of a query among a large number of records. To demonstrate the algorithm, we simulated X-band scattering from ten civilian vehicles placed throughout a large scene, varying elevation angles in the 35 to 59 degree range. We achieved better than 98 percent classification performance. We also classified seven vehicles in a 2006 public release data collection with 100% success.

[1]  Emre Ertin,et al.  Polarimetric classification of scattering centers using M-ary Bayesian decision rules , 2000, IEEE Trans. Aerosp. Electron. Syst..

[2]  Bir Bhanu,et al.  Increasing the discrimination of synthetic aperture radar recognition models , 2002 .

[3]  Lee C. Potter,et al.  Discrimination of civilian vehicles using wide-angle SAR , 2008, SPIE Defense + Commercial Sensing.

[4]  W. Eric L. Grimson,et al.  Probabilistic optimization approach to SAR feature matching , 1996, Defense, Security, and Sensing.

[5]  Dong-Gyu Sim,et al.  Object matching algorithms using robust Hausdorff distance measures , 1999, IEEE Trans. Image Process..

[6]  D. Giuli,et al.  Polarization diversity in radars , 1986, Proceedings of the IEEE.

[7]  W. Eric L. Grimson,et al.  Bounding performance of peak-based target detectors , 1997, Defense, Security, and Sensing.

[8]  Charles V. Jakowatz,et al.  Beamforming as a foundation for spotlight-mode SAR image formation by backprojection , 2008, SPIE Defense + Commercial Sensing.

[9]  Trevor Darrell,et al.  The Pyramid Match Kernel: Efficient Learning with Sets of Features , 2007, J. Mach. Learn. Res..

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

[11]  Anil K. Jain,et al.  On matching latent fingerprints , 2008, 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[12]  Lee C. Potter,et al.  Attributed scattering centers for SAR ATR , 1997, IEEE Trans. Image Process..

[13]  Charles V. Jakowatz,et al.  Spotlight-Mode Synthetic Aperture Radar: A Signal Processing Approach , 1996 .

[14]  Dominick A. Giglio.  Algorithms for Synthetic Aperture Radar Imagery , 1994 .

[15]  Lee C. Potter,et al.  Civilian vehicle radar data domes , 2010, Defense + Commercial Sensing.

[16]  J. Keller,et al.  Geometrical theory of diffraction. , 1962, Journal of the Optical Society of America.

[17]  Peter E. Buxa,et al.  Implementation and analysis of a fast backprojection algorithm , 2006, SPIE Defense + Commercial Sensing.

[18]  Ludmila I. Kuncheva,et al.  A Theoretical Study on Six Classifier Fusion Strategies , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[19]  G. J. Owirka,et al.  Optimal polarimetric processing for enhanced target detection , 1991, NTC '91 - National Telesystems Conference Proceedings.

[20]  Joseph A. O'Sullivan,et al.  Statistical assessment of model fit for synthetic aperture radar data , 2001, SPIE Defense + Commercial Sensing.

[21]  Lee C. Potter,et al.  Model-based Bayesian feature matching with application to synthetic aperture radar target recognition , 2001, Pattern Recognit..

[22]  Rong Wang,et al.  Composite class models for SAR recognition , 2003, SPIE Defense + Commercial Sensing.

[23]  Lee C. Potter,et al.  Classifying civilian vehicles using a wide-field circular SAR , 2009, Defense + Commercial Sensing.

[24]  Trevor Darrell,et al.  Pyramid Match Hashing: Sub-Linear Time Indexing Over Partial Correspondences , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[25]  Makoto Matsumoto,et al.  SIMD-Oriented Fast Mersenne Twister: a 128-bit Pseudorandom Number Generator , 2008 .

[26]  Charles V. Jakowatz,et al.  An implementation of a fast backprojection image formation algorithm for spotlight-mode SAR , 2008, SPIE Defense + Commercial Sensing.

[27]  William C. Snyder,et al.  Model-based fusion of multi-look SAR for ATR , 2002, SPIE Defense + Commercial Sensing.

[28]  Larry L. Horowitz,et al.  Benefits of aspect diversity for SAR ATR: fundamental and experimental results , 2000, SPIE Defense + Commercial Sensing.

[29]  LeRoy A. Gorham,et al.  A challenge problem for 2D/3D imaging of targets from a volumetric data set in an urban environment , 2007, SPIE Defense + Commercial Sensing.

[30]  Pauli Kuosmanen,et al.  Fingerprint Matching Using an Orientation-Based Minutia Descriptor , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[31]  Jiri Matas,et al.  On Combining Classifiers , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[32]  Bir Bhanu,et al.  Exploiting azimuthal variance of scatterers for multiple-look SAR recognition , 2002, SPIE Defense + Commercial Sensing.