Advertisement

Statistical feature modelling for active contours

  • Simon Rowe
  • Andrew Blake
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1065)

Abstract

A method is proposed of robust feature-detection for visual tracking. Frequently strong background clutter competes with foreground features and may succeed in pulling a tracker off target. This effect may be avoided by modelling the appearance of the foreground object (the target). The model consists of probability density functions of intensity along curve normals—a form of statistical template. The model can then be located by the use of a dynamic programming algorithm—even in the presence of substantial image distortions. Practical tests with contour tracking show marked improvement over simple feature detection techniques.

Keywords

Dynamic Programming Search Line Active Contour Dynamic Programming Algorithm Foreground Object 
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.
    A. Amini, S. Tehrani, and T. Weymouth. Using dynamic programming for minimizing the energy of active contours in the presence of hard constraints. In Proc. 2nd Int. Conf. on Computer Vision, 95–99, 1988.Google Scholar
  2. 2.
    B. Bascle and R. Deriche. Region tracking through image sequences. In Proc. 5th Int. Conf. on Computer Vision, 302–307, Cambridge, MA. IEEE, IEEE Computer Society, June 1995.Google Scholar
  3. 3.
    A. Blake, R. Curwen, and A. Zisserman. Affine-invarient contour tracking with automatic control of spatiotemporal scale. In Proc. 4th Int. Conf. on Computer Vision, 66–95, Berlin. IEEE, IEEE Computer Society, May 1993.Google Scholar
  4. 4.
    T. Cootes, C. Taylor, A. Lanitis, D. Cooper, and J. Graham. Buiding and using flexible models incorporating grey-level information. In Proc. 4th Int. Conf. on Computer Vision, 242–246, Berlin. IEEE, IEEE Computer Society, May 1993.Google Scholar
  5. 5.
    T. H. Cormen, C. E. Leiserson, and R. L. Rivest. Introduction to Algorithms. McGraw-Hill, 1992.Google Scholar
  6. 6.
    J. Foley, A. van Dam, S. Feiner, and J. Hughes. Computer Graphics, principles and practice. Addison Wesley, 2nd edition, 1990.Google Scholar
  7. 7.
    A. Gelb, editor. Applied Optimal Estimation. MIT Press, Cambridge, MA, 1974.Google Scholar
  8. 8.
    M. Kass, A. Witkin, and D. Terzopoulos. Snakes:active contour models. In Proc. 1st Int. Conf. on Computer Vision, 259–268, 1987.Google Scholar
  9. 9.
    S. Rowe and A. Blake. Statistical background models for tracking with a virtual camera. In D.Pycock, editor, British Machine Vision Conference 1995, volume 2, 423–432. BMVA, Sept 1995.Google Scholar
  10. 10.
    D. Terzopoulos and R. Szeliski. Tracking with Kalman snakes. In A. Blake and A. Yuille, editors, Active Vision, 3–20. The MIT Press, 1993.Google Scholar
  11. 11.
    P. Woods, C. Taylor, D. Cooper, and R. Dixon. The use of geometric and grey-level models for industrial inspection. Pattern Recognition Letters, 5(1):11–17, Jan 1987.Google Scholar
  12. 12.
    A. Yuille and P. Hallinan. Deformable templates. In A. Blake and A. Yuille, editors, Active Vision, 20–38. The MIT Press, 1993.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1996

Authors and Affiliations

  • Simon Rowe
    • 1
  • Andrew Blake
    • 1
  1. 1.Dept. of Engineering ScienceOxford UniversityOxfordUK

Personalised recommendations