Advertisement

Segmentations of Spatio-Temporal Images by Spatio-Temporal Markov Random Field Model

  • Shunsuke Kamijo
  • Katsushi Ikeuchi
  • Masao Sakauchi
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2134)

Abstract

There have been many successful researches on image segmentations that employ Markov Random Field model. However, most of them were interested in two-dimensional MRF, or spatial MRF, and very few researches are interested in three-dimensional MRF model. Generally, ’three-dimensional’ have two meaning, that are spatially three-dimensional and spatio-temporal. In this paper, we especially are interested in segmentations of spatio-temporal images which appears to be equivalent to tracking problem of moving objects such as vehicles etc. For that purpose, by extending usual two-dimensional MRF, we defined a dedicated three-dimensional MRF which we defined as Spatio-Temporal MRF model(S-T MRF). This S-T MRF models a tracking problem by determining labels of groups of pixels by referring to their texture and labeling correlations along the temporal axis as well as the x-y image axes.Although vehicles severely occlude each other in general traffic images,segmentation boundaries of vehicle regions will be determined precisely by this S-T MRF optimizing such boundaries through spatio-temporal images. Consequently, it was proved that the algorithm has performed 95% success of tracking in middle-angle image at an intersection and 91% success in low-angle and front-view images at a highway junction.

Keywords

Motion Vector Markov Random Field Temporal Axis Tracking Problem Consecutive Image 
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.

Rerences

  1. 1.
    Natan Peterfreund, ”Robust Tracking of Position and Velocity With Kalman Snakes” IEEE Trans. Pattern Analysis and Machine Intelligence(PAMI), Vol. 21 No. 6, 1999, pp. 564–569.CrossRefGoogle Scholar
  2. 2.
    M. Kass, A. Witkin,and D. Terzopoulos, “Snakes: Active contour models” Int’l J. Computer Vision, Vol. 1, 1988, pp. 321–331.CrossRefGoogle Scholar
  3. 3.
    S.M. Smith and J.M. Brady, ” ASSET-2:Real-Time Motion Segmentation and Shape Tracking”, IEEE Trans. Pattern Analysis and Machine Intelligence(PAMI), Vol. 17 No. 8, 1995, pp. 814–820.CrossRefGoogle Scholar
  4. 4.
    C. Stauffer and W.E.L. Grimson, “Adaptive background mixture models for realtime tracking”, Proc. of CVPR 1999, Jun 1999, pp246–252.Google Scholar
  5. 5.
    Holger Leuck and Hans-Hellmut Nagel, ”Automatic Differentiation Facilitates OF-Integration into Steering-Angle-Based Road Vehicle Tracking”, Proc. of Conputer Vision and Pattern Recognition(CVPR)’ 99, pp. 360–365.Google Scholar
  6. 6.
    Warren F. Gardner and Daryl T. Lawton ”Interactive Model-Based Vehicle Tracking”, IEEE Trans. PAMI, Vol. 18 No. 11, 1996, pp. 1115–1121.Google Scholar
  7. 7.
    N. Metropolis, A.W. Rosenbluth, M.N. Rosenbluth, A.H. Teller and E. Teller, “Equations of State calculations by fast computing machines”, J.Chem.Phys., Vol21, pp1087–1091, 1953.CrossRefGoogle Scholar
  8. 8.
    S. Kirkpatrick, C.D. Gelatt and M.P. Vecci, “Optimization by Simulated Annealing”, Science, 220, pp671–680, 1983.CrossRefMathSciNetGoogle Scholar
  9. 9.
    S. Geman and D. Geman, “Stochastic Relaxation, Gibbs Distribution, and the Bayesian Restoration of images”, IEEE trans. PAMI, Vol. 6, No. 6, pp 721–741, 1984.zbMATHGoogle Scholar
  10. 10.
    R. Chellappa, S. Chatterjee and R. Bargdzian, “Texture Synthesis and Compression Using Gaussian-Markov Random Field Models”, IEEE trans. SMC, Vol. 15, No. 2, 1985.Google Scholar
  11. 11.
    D.K. Panjwani and G. Healey, “Markov random field models for unsupervised segmentation of textured color images”, IEEE Trans. PAMI, vol. 17, no. 10, pp939–954, 1995.Google Scholar
  12. 12.
    D.K. Panjwani and G. Healey, “Selecting neighbors in random field models for color images,” Proc. ICIP, vol. II, pp56–60, 1994.Google Scholar
  13. 13.
    B.S. Majunath and R. Chellappa, “Unsupervised Texture Segmentation Using Markov Random Field Models”, IEEE Trans. PAMI, vol. 13, no. 5, pp478–482, May 1991.Google Scholar
  14. 14.
    R. Hu and M.N. Fahmy, “Texture Segmentation based on a Hierarchical Markov Random Field Model”, Signal Processing, vol. 26, pp. 285–305, 1992.CrossRefGoogle Scholar
  15. 15.
    F.S. Cohen and Z. Fan, “Maximum Likelihood Unsupervised Texture Image Segmentation”, CVGIP: Graphical Models and Image Processing, vol. 54, no. 3, pp239–251, 1992.CrossRefGoogle Scholar
  16. 16.
    P. Andrey, P. Tarroux, “Unsupervised Segmentation of Markov Radom Field Modeled Textured Images Using Selectionist Relaxation”, IEEE trans. PAMI, Vol20, No. 3, 1998.Google Scholar
  17. 17.
    S.A. Barker and P.J.W. Rayner, “Unsupervised Image Segmentation Using Markov Random Field Models”, Proc. EMMCVPR’99(Lecture Notes in CS printed by Springer), pp179–194, May 1997.Google Scholar
  18. 18.
    P. Rostaing, J.N. Provost and C. Collet, “Unsupervised Multispectral Image Segmentation Using Generalized Gaussian Noise Model., Proc. EMM-CVPR’99(Lecture Notes in CS printed by Springer), pp142–156, July 1999.Google Scholar
  19. 19.
    Rama Chellappa and Anil Jain, “Markov Random Fields: Theory and Application”, Academic Press, 1993.Google Scholar
  20. 20.
    S. Kamijo, Y. Matsushita, K. Ikeuchi, M. Sakauchi, “Traffic Monitoring and Accident Detection at Intersections”, IEEE trans. ITS, Vol. 1 No. 2, June. 2000, pp108–118.Google Scholar
  21. 21.
    S. Kamijo, Y. Matsushita, K. Ikeuchi, M. Sakauchi, “Occlusion Robust Tracking utilizing Spatio-Temporal Markov Random Field Model”, International Conference on Pattern Recognition(ICPR), Barcelona, Sep. 2000, Vol. 1 pp142–147.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • Shunsuke Kamijo
    • 1
  • Katsushi Ikeuchi
    • 1
  • Masao Sakauchi
    • 1
  1. 1.Institute of Industrial ScienceUniversity of TokyoTokyoJapan

Personalised recommendations