Stochastic Models for Recognition of Occluded Objects

  • Bir Bhanu
  • Yingqiang Lin
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1876)

Abstract

Recognition of occluded objects in synthetic aperture radar (SAR) images is a significant problem for automatic object recognition. Stochastic models provide some attractive features for pattern matching and recognition under partial occlusion and noise. In this paper, we present a hidden Markov modeling (HMM) based approach for recognizing objects in synthetic aperture radar (SAR) images. We identify the peculiar characteristics of a SAR sensor and using these characteristics we develop feature based multiple stochastic models for a given SAR image of an object. The models exploiting the relative geometry of feature locations or the amplitude of scattering centers in SAR radar return are based on sequentialization of scattering centers extracted from SAR images. In order to improve performance under real world situations, we integrate these models synergistically using their probabilistic estimates for recognition of a particular object at a specific azimuth. Experimental results are presented using real SAR images with varying amount of occlusion.

Keywords

hidden Markov modeling object recognition multiple recognition models SAR images 

References

  1. 1.
    B. Bhanu, D.E. Dudgeon, E.G. Zelnio, A. Rosenfeld, D. Casasent and I.S. Reed. Introduction to the special issue on automatic target recognition. IEEE Transactions on Image Processing, Vol. 6, No. 1, January 1997Google Scholar
  2. 2.
    L.R. Rabiner and B.H. Juang. An introduction to hidden Markov models. IEEE ASSP Magazine, 3(1):4–16, Jan 1986.Google Scholar
  3. 3.
    O.E. Agazzi and S.S. Kuo. Hidden Markov model based optical character recognition in the presence of deterministic transformations. Pattern Recognition, 26(12):1813–1826, November 1993.Google Scholar
  4. 4.
    W. Burger and B. Bhanu. Signal-to-symbol conversion for structural object recognition using hidden Markov models. Proc. ARPA Image Understanding Workshop, Monterey, CA, November 13–16, pp. 1287–1291, 1994.Google Scholar
  5. 5.
    D.P. Kottke et al. A design for HMM-based SAR ATR. SPIE Conf. on Algorithm for Synthetic Aperture Radar Imagery V, Vol. 3370, pp. 541–551, April 1998.Google Scholar
  6. 6.
    K.H. Fielding and D.W. Ruck. Spatio-temporal pattern recognition using hidden Markov models. IEEE Trans. Aerospace and Electronic Systems, 31(4):1292–1300, 1995.CrossRefGoogle Scholar
  7. 7.
    R.R. Rao and R.M. Mersereau. On merging hidden Markov models with deformable templates. In Proc. International Conf. on Image Processing, pages 556–559, 1995.Google Scholar
  8. 8.
    L. Novak, G. Owirka and C. Netishen. Radar target identification using spatial matched filters. Pattern Recognition, Vol. 27, No. 4, pp. 607–614, 1994.CrossRefGoogle Scholar
  9. 9.
    J. Yi, B. Bhanu and M. Li. Target indexing in SAR image using scattering centers and Hausdoff distance. Pattern Recognition Letters, Vol. 17, pp. 1191–1198, Sept. 1996.Google Scholar
  10. 10.
    G. Jones III and B. Bhanu. Recognition of Articulated and Occluded Objects. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 21, No. 7, pp. 603–613, July 1999.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2000

Authors and Affiliations

  • Bir Bhanu
    • 1
  • Yingqiang Lin
    • 1
  1. 1.Center for Research in Intelligent SystemsUniversity of CaliforniaRiversideUSA

Personalised recommendations