Statistical Foreground Modelling for Object Localisation

  • Josephine Sullivan
  • Andrew Blake
  • Jens Rittscher
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1843)


A Bayesian approach to object localisation is feasible given suitable likelihood models for image observations. Such a likelihood involves statistical modelling - and learning - both of the object foreground and of the scene background. Statistical background models are already quite well understood. Here we propose a “conditioned likelihood” model for the foreground, conditioned on variations both in object appearance and illumination. Its effectiveness in localising a variety of objects is demonstrated.


Layered Sampling Conditioned Likelihood Importance Function Pattern Theory Factor Sampling 
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.


  1. 1.
    R. Baddeley. Searching for filters with interesting output distributions: an uninteresting direction to explore?. Network, 7(2):409–421, 1996.CrossRefGoogle Scholar
  2. 2.
    R.H. Bartels, J.C. Beatty, and B.A. Barsky. An Introduction to Splines for use in Computer Graphics and Geometric Modeling. Morgan Kaufmann, 1987.Google Scholar
  3. 3.
    B. Bascle and A. Blake. Separability of pose and expression in facial tracking and animation. In Proc. 6th Int. Conf. on Computer Vision, pages 323–328, 1998.Google Scholar
  4. 4.
    B. Bascle and R. Deriche. Region tracking through image sequences. In Proc. 5th Int. Conf. on Computer Vision, pages 302–307, Boston, Jun 1995.Google Scholar
  5. 5.
    P.N. Belhumeur and D.J. Kriegman. What is the set of images of an object under all possible illumination conditions. Int. J. Computer Vision, 28(3):245–260, 1998.CrossRefGoogle Scholar
  6. 6.
    A.J. Bell and T.J. Sejnowski. Edges are the independent components of natural scenes. In Advances in Neural Information Processing Systems, volume 9, pages 831–837. MIT Press, 1997.Google Scholar
  7. 7.
    A. Blake and M. Isard. Active contours. Springer, 1998.Google Scholar
  8. 8.
    F.L. Bookstein. Principal warps:thin-plate splines and the decomposition of deformations. IEEE Trans. on Pattern Analysis and Machine Intelligence, 11(6):567–585, 1989.zbMATHCrossRefGoogle Scholar
  9. 9.
    P.J. Burt. Fast algorithms for estimating local image properties. Computer Vision, Graphics and Image Processing, 21:368–382, 1983.CrossRefGoogle Scholar
  10. 10.
    T.F. Cootes, C.J. Taylor, D.H. Cooper, and J. Graham. Active shape models-their training and application. Computer Vision and Image Understanding, 61(1):38–59, 1995.CrossRefGoogle Scholar
  11. 11.
    D.J. Field. Relations between the statistics of natural images and the response properties of cortical cells. J. Optical Soc. of America A., 4:2379–2394, 1987.Google Scholar
  12. 12.
    W.T. Freeman. The generic viewpoint assumption in a framework for visual perception. Nature, 368:542–545, 1996.CrossRefGoogle Scholar
  13. 13.
    W.T. Freeman and J.B. Tenenbaum. Learning bilinear models for two-factor problems in vision. In Proc. Conf. Computer Vision and Pattern Recognition, pages 554–560, June 1997.Google Scholar
  14. 14.
    D. Geman and B. Jedynak. An active testing model for tracking roads in satellite images. IEEE Trans. on Pattern Analysis and Machine Intelligence, 18(1): 1–14, 1996.CrossRefGoogle Scholar
  15. 15.
    U. Grenander. Lectures in Pattern Theory I, II and III. Springer, 1976–1981.Google Scholar
  16. 16.
    U. Grenander, Y. Chow, and D.M. Keenan. HANDS. A Pattern Theoretical Study of Biological Shapes. Springer-Verlag. New York, 1991.Google Scholar
  17. 17.
    G.D. Hager and K. Toyama. Xvision: combining image warping and geometric constraints for fast tracking. In Proc. 4th European Conf. Computer Vision, pages 507–517, 1996.Google Scholar
  18. 18.
    J.M. Hammersley and D.C. Handscomb. Monte Carlo methods. Methuen, 1964.Google Scholar
  19. 19.
    A. Lanitis, C.J. Taylor, and T.F. Cootes. A unified approach to coding and interpreting face images. In Proc. 5th Int. Conf. on Computer Vision, pages 368–373, 1995.Google Scholar
  20. 20.
    D.J.C. Mac Kay. Bayesian Methods for Adaptive Models. PhD thesis, California Institute of Technology, 1992.Google Scholar
  21. 21.
    D. Mumford. Pattern theory: a unifying perspective. In D.C. Knill and W. Richard, editors, Perception as Bayesian inference, pages 25–62. Cambridge University Press, 1996.Google Scholar
  22. 22.
    B. A. Olshausen and D.J. Field. Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature, 381:607–609, 1996.CrossRefGoogle Scholar
  23. 23.
    P. Perona. Steerable-scalable kernels for edge detection and junction analysis. J. Image and Vision Computing, 10(10):663–672, 1992.CrossRefGoogle Scholar
  24. 24.
    S.M. Rowe and A. Blake. Statistical mosaics for tracking. J. Image and Vision Computing, 14:549–564, 1996.CrossRefGoogle Scholar
  25. 25.
    E.P. Simoncelli. Modeling surround suppression in V1 neurons with a statistically-derived normalization model. In Advances in Neural Information Processing Systems, volume 11, page in press. MIT Press, 1997.Google Scholar
  26. 26.
    J. Sullivan, A. Blake, M. Isard, and J. MacCormick. Object localization by bayesian correlation. In Proc. 7th Int. Conf. on Computer Vision, volume 2, pages 1068–1075, 1999.CrossRefGoogle Scholar
  27. 27.
    P. Viola and W.M. Wells. Alignment by maximisation of mutual information. In Proc. 5th Int. Conf. on Computer Vision, pages 16–23, 1993.Google Scholar
  28. 28.
    S.C. Zhu and D. Mumford. GRADE: Gibbs reaction and diffusion equation. IEEE Trans. on Pattern Analysis and Machine Intelligence, 19(11): 1236–1250, 1997.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2000

Authors and Affiliations

  • Josephine Sullivan
    • 1
  • Andrew Blake
    • 2
  • Jens Rittscher
    • 1
  1. 1.Dept. of EngineeringOxford UniversityOxfordUK
  2. 2.Microsoft Research LdCambridgeUK

Personalised recommendations