Advertisement

Tracking with the EM Contour Algorithm

  • Arthur E. C. Pece
  • Anthony D. Worrall
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2350)

Abstract

A novel active-contour method is presented and applied to pose refinement and tracking. The main innovation is that no ”features” are detected at any stage: contours are simply assumed to remove statistical dependencies between pixels on opposite sides of the contour. This assumption, together with a simple model of shape variability of the geometric models, leads to the application of an EM method for maximizing the likelihood of pose parameters. In addition, a dynamical model of the system leads to the application of a Kalman filter. The method is demonstrated by tracking motor vehicles with 3-D models.

Keywords

Ground Plane Active Contour Object Boundary Image Location Observation Model 
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.

References

  1. 1.
    Y. Bar-Shalom, T. E. Fortmann, Tracking And Data Association. Academic Press, 1988.Google Scholar
  2. 2.
    A. Baumberg, D.C. Hogg, Learning Flexible Models from Image Sequences, Proc. of ECCV’94, Lecture Notes in Computer Science, vol. 800, pp. 299–308, 1994.Google Scholar
  3. 3.
    A Blake, M Isard, Active Contours, Springer-Verlag, Berlin 1998.Google Scholar
  4. 4.
    A.P. Dempster, N.M. Laird, D.B. Rubin, Maximum likelihood from incomplete data via the EM algorithm (with discussion), J. of the Royal Statistical Soc. B 39: 1–38, 1977.MathSciNetGoogle Scholar
  5. 5.
    JM Ferryman, AD Worrall, Proc. of the 1st IEEE International Workshop on Performance Evaluation in Tracking and Surveillance: PETS 2000.Google Scholar
  6. 6.
    D Geman, B Jedynak, An active testing model for tracking roads in satellite images. IEEE Trans. PAMI 18(1): 1–14, 1996.Google Scholar
  7. 7.
    C Harris, Tracking with rigid models. In Active Vision (A Blake, A Yuille, eds) pp. 59–73. MIT Press, 1992.Google Scholar
  8. 8.
    J. Huang, D. Mumford, Statistics of natural images and models. In Proc. CVPR’99, vol. 1, pp. 541–547, 1999.Google Scholar
  9. 9.
    A. Lee, D. Mumford, An Occlusion Model generating Scale-Invariant Images. In Proc. Int. Workshop on Statistical and Computational Theories of Vision. http://www.cis.ohio-state.edu/ szhu/SCTV2001.html, 1999.
  10. 10.
    M Kass, A Witkin, D Terzopoulos, Snakes: active contour models. In Proc. ICCV’97, pp. 259–268, 1987.Google Scholar
  11. 11.
    D Koller, K Daniilidis, H-H Nagel, Model-based object tracking in monocular image sequences of road traffic scenes. Int.J.Comp.Vis. 10(3): 257–281, 1993.CrossRefGoogle Scholar
  12. 12.
    H Kollnig, H-H Nagel, 3D pose estimation by fitting image gradients directly to polyhedral models. In Proc. ICCV’95, pp.569–574, 1995.Google Scholar
  13. 13.
    G.J. McLachlan, T. Krishnan, The EM Algorithm and Extensions, Wiley, New York, 1997.zbMATHGoogle Scholar
  14. 14.
    A.E.C. Pece, Generative-model-based tracking by cluster analysis of image differences. Accepted for publication in Robotics and Autonomous Systems.Google Scholar
  15. 15.
    AEC Pece, AD Worrall, A statistically-based Newton method for pose refinement. Image and Vision Computing 16: 541–544, 1998.CrossRefGoogle Scholar
  16. 16.
    AEC Pece, AD Worrall, A Newton method for pose refinement of 3D models. Proc 6th International Symposium on Intelligent Robotic Systems: SIRS’98, The University of Edinburgh.Google Scholar
  17. 17.
    A.E.C. Pece, A.D. Worrall, Tracking without feature detection. In[5], pp. 29–37, 2000.Google Scholar
  18. 18.
    DL Ruderman, The statistics of natural images. Network 5: 517–548, 1994.zbMATHCrossRefGoogle Scholar
  19. 19.
    H. Sidenbladh, M.J. Black, Learning image statistics for Bayesian tracking, In Proc. ICCV’01, Vol. 2, pp. 709–716, 2001.Google Scholar
  20. 20.
    P. Tissainayagam, D. Suter, Tracking multiple object contour with automatic motion model switching, In Proc. ICPR’00, pp. 1146–1149, 2000.Google Scholar
  21. 21.
    AD Worrall, JM Ferryman, GD Sullivan, KD Baker, Pose and structure recovery using active models. Proc. BMVC’95, pp. 137–146, 1995.Google Scholar
  22. 22.
    AL Yuille, JM Coughlan, Fundamental limits of Bayesian inference: order parameters and phase transitions for road tracking. IEEE Trans. PAMI 22(2): 160–173, 2000.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Arthur E. C. Pece
    • 1
  • Anthony D. Worrall
    • 2
  1. 1.Institute of Computer ScienceUniversity of CopenhagenCopenhagenDenmark
  2. 2.Department of Computer ScienceUniversity of ReadingReadingEngland

Personalised recommendations