Advertisement

Methods for Improving the Performance of an SAR Recognition System

  • Bir Bhanu
  • Grinnell JonesIII
Chapter
Part of the Advances in Pattern Recognition book series (ACVPR)

Summary

The focus of this chapter is on methods for improving the performance of a model-based system for recognizing vehicles in synthetic aperture radar (SAR) imagery under the extended operating conditions of object articulation, occlusion, and configuration variants. The fundamental approach uses recognition models based on quasi-invariant local features, radar scattering center locations, and magnitudes. Three basic extensions to this approach are discussed: (1) incorporation of additional features; (2) exploitation of a priori knowledge of object similarity represented and stored in the model-base; and (3) integration of multiple recognizers at different look angles. Extensive experimental recognition results are presented in terms of receiver operating characteristic (ROC) curves to show the effects of these extensions on SAR recognition performance for real vehicle targets with articulation, configuration variants, and occlusion.

Keywords

Synthetic Aperture Radar Synthetic Aperture Radar Image Occlude Object Unweighted Case Scatterer Location 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    Ross, T., Worrell, S., Velten, V., Mossing, J., Bryant, M.: Standard SAR ATR evaluation experiments using the MSTAR public release data set. In: SPIE Proceedings: Algorithms for Synthetic Aperture Radar Imagery V. Volume 3370. (1998) 566–573Google Scholar
  2. [2]
    Carlson, D., Kumar, B., Mitchell, R., Hoffelder, M.: Optimal trade-off distance classifier correlation filters (OTDCCFs) for synthetic aperture radar automatic target recognition. In: SPIE Proceedings: Algorithms for Synthetic Aperture Radar Imagery IV. Volume 3070. (1997) 110–120Google Scholar
  3. [3]
    Casasent, D., Shenoy, R.: Synthetic aperture radar detection and clutter rejection MINACE filters. Pattern Recognition 30 (1997) 151–162CrossRefGoogle Scholar
  4. [4]
    Meth, R., Chellappa, R.: Automatic classification of targets in synthetic aperture radar imagery using topographic features. In: SPIE Proceedings: Algorithms for SAR Imagery III. Volume 2757. (1996) 186–193Google Scholar
  5. [5]
    Ryan, T., Egaas, B.: SAR target indexing with hierarchical distance transforms. In: SPIE Proceedings: Algorithms for Synthetic Aperture Radar Imagery III. Volume 2757. (1996) 243–252Google Scholar
  6. [6]
    Verly, J., Delanoy, R., Lazott, C.: Principles and evaluation of an automatic target recognition system for synthetic aperture radar imagery based on the use of functional templates. In: SPIE Proceedings: Automatic Target Recognition III. Volume 1960., Orlando, FL (1993) 57–71Google Scholar
  7. [7]
    Casasent, D., Shenoy, R.: Feature space trajectory for distorted-object classification and pose estimation in SAR. Optical Engineering 36 (1997) 2719–2728Google Scholar
  8. [8]
    Yi, J.H., Bhanu, B., Li, M.: Target indexing in SAR images using scattering centers and the Hausdorff distance. Pattern Recognition Letters 17 (1996) 1191–1198Google Scholar
  9. [9]
    Bhanu, B., Jones, G.: Recognizing target variations and articulations in synthetic aperture radar images. Optical Engineering 39 (2000) 712–723CrossRefGoogle Scholar
  10. [10]
    Jones, G., Bhanu, B.: Recognizing articulated targets in SAR images. Pattern Recognition 34 (2001) 469–485Google Scholar
  11. [11]
    Jones, G., Bhanu, B.: Recognizing occluded objects in SAR images. IEEE Transactions on Aerospace and Electronic Systems 37 (2001) 316–328CrossRefGoogle Scholar
  12. [12]
    III, G.J., Bhanu, B.: Recognition of articulated and occluded objects. IEEE Transactions on Pattern Analysis and Machine Intelligence 21 (1999) 603–613CrossRefGoogle Scholar
  13. [13]
    Boshra, M., Bhanu, B.: Predicting an upper bound on performance of target recognition in SAR images. IEEE Transactions on Aerospace and Electronic Systems 37 (2001) 876–888CrossRefGoogle Scholar
  14. [14]
    : Khoros Pro v2.2 User’s Guide. Addison-Wesley-Longman (1998)Google Scholar
  15. [15]
    Dudgeon, D., Lacoss, R., Lazott, C., Verly, J.: Use of persistent scatterers for model-based recognition. In: SPIE Proceedings: Algorithms for Synthetic Aperture Radar Imagery. Volume 2230., Orlando, FL (1994) 356–368Google Scholar
  16. [16]
    Novak, L., Halversen, S., Owirka, G., Hiett, M.: Effects of polarization and resolution on SAR ATR. IEEE Transactions on Aerospace and Electronic Systems 33 (1997) 102–115CrossRefGoogle Scholar
  17. [17]
    Ikeuchi, K., Shakungaa, T., Wheelera, M., Yamazaki, T.: Invariant histograms and deformable template matching for SAR target recognition. In: Proc. IEEE Conf. on Comp. Vision and Pattern Rec. (1996) 100–105Google Scholar
  18. [18]
    Mossing, J., Ross, T.: An evaluation of SAR ATR algorithm performance sensitivity to MSTAR extended operating conditions. In: SPIE Proceedings: Algorithms for SAR Imagery V. Volume 3370. (1998) 554–565Google Scholar
  19. [19]
    Wissinger, J., Ristroph, R., Diemunsch, J., Severson, W., Freudenthal, E.: MSTAR’s extensible search engine and inferencing toolkit. In: SPIE Proceedings: Algorithms for SAR Imagery VI. Volume 3721. (1999) 554–570Google Scholar
  20. [20]
    Lamden, Y., Wolfson, H.: Geometric hashing: A general and efficient model-based recognition scheme. In: Proc. International Conference on Computer Vision. (1988) 238–249Google Scholar
  21. [21]
    Grimson, W.E.L.: Object Recognition by Computer: The Role of Geometric Constraints. The MIT Press, Cambridge, MA (1990)Google Scholar
  22. [22]
    Bhanu, B., Lin, Y., Jones, G., Peng, J.: Adaptive target recognition. Machine Vision and Applications 11 (2000) 289–299Google Scholar

Copyright information

© Springer-Verlag London Limited 2005

Authors and Affiliations

  • Bir Bhanu
    • 1
  • Grinnell JonesIII
    • 1
  1. 1.Center for Research in Intelligent SystemsUniversity of CaliforniaRiverside

Personalised recommendations