Advertisement

The Trace Model for Object Detection and Tracking

  • Sachin Gangaputra
  • Donald Geman
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4170)

Abstract

We introduce a stochastic model to characterize the online computational process of an object recognition system based on a hierarchy of classifiers. The model is a graphical network for the conditional distribution, under both object and background hypotheses, of the classifiers which are executed during a coarse-to-fine search. A likelihood is then assigned to each history or “trace” of processing. In this way, likelihood ratios provide a measure of confidence for each candidate detection, which markedly improves the selectivity of hierarchical search, as illustrated by pruning many false positives in a face detection experiment. This also leads to a united framework for object detection and tracking. Experiments in tracking faces in image sequences demonstrate invariance to large face movements, partial occlusions, changes in illumination and varying numbers of faces.

Keywords

Video Sequence Object Detection Face Detection Gesture Recognition Trace Distribution 
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.

References

  1. 1.
    Amit, Y.: 2D Object Detection and Recognition. MIT Press, Cambridge (2002)Google Scholar
  2. 2.
    Amit, Y., Geman, D., Fan, X.: A coarse-to-fine strategy for pattern recognition. IEEE Trans. PAMI 26(12), 1606–1621 (2004)Google Scholar
  3. 3.
    Blanchard, G., Geman, D.: Sequential testing designs for pattern recognition. Annals of Statistics 33, 155–1202 (2005)CrossRefMathSciNetGoogle Scholar
  4. 4.
    Burl, M., Perona, P.: Recognition of planar object classes. In: IEEE Proc. CVPR, pp. 223–230 (1996)Google Scholar
  5. 5.
    Cascia, M.L., Sclaroff, S., Athitos, V.: Fast reliable head tracking under varying illumination: An approach based on registration of texture-mapped 3D models. IEEE. Trans. PAMI 21(6) (1999)Google Scholar
  6. 6.
    Comaniciu, D., Ramesh, V., Meer, P.: Kernel based object tracking. IEEE Trans. PAMI 25, 564–577 (2003)Google Scholar
  7. 7.
    Decarlo, D., Metaxas, D.: Deformable model based face shape and motion estimation. In: Proc. Int’l Conf. Auto. Face and Gesture Recognition (1996)Google Scholar
  8. 8.
    Duda, R., Hart, P., Stork, D.: Pattern Classification. John Wiley and Sons, Chichester (2001)MATHGoogle Scholar
  9. 9.
    Edwards, C.J., Taylor, C.J., Cootes, T.F.: Learning to identify and track faces in an image sequence. In: Proc. Int’l Conf. Auto. Face and Gesture Recognition, pp. 260–265 (1998)Google Scholar
  10. 10.
    Fleuret, F., Geman, D.: Coarse-to-fine face detection. IJCV 41, 85–107 (2001)MATHCrossRefGoogle Scholar
  11. 11.
    Geman, S., Potter, D., Chi, Z.: Composition systems. Quaterly of Applied Mathematics LX, 707–736 (2002)MathSciNetGoogle Scholar
  12. 12.
    Isard, M., Blake, A.: Condensation-conditional density propagation for visual tracking. IJCV 29, 5–28 (1998)CrossRefGoogle Scholar
  13. 13.
    Krempp, S., Geman, D., Amit, Y.: Sequential learning with reusable parts for object detection, Technical Report, Johns Hopkins University (2002)Google Scholar
  14. 14.
    Li, B., Chellappa, R.: A generic approach to simultaneous tracking and verification in video. IEEE Trans. Image Processing 11, 530–544 (2002)CrossRefGoogle Scholar
  15. 15.
    Osuna, E., Freund, R., Girosi, F.: Training support vector machines: an application to face detection. In: Proc. IEEE CVPR, pp. 130–136 (1997)Google Scholar
  16. 16.
    Pearl, J.: Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann, San Francisco (1988)Google Scholar
  17. 17.
    Rowley, H., Baluja, S., Kanade, T.: Neural network-based face detection. IEEE Trans. PAMI 20, 23–38 (1998)Google Scholar
  18. 18.
    Sahbi, H.: Coarse-to-fine support vector machines for hierarchical face detection. Ph.D thesis, Versailles University (2003)Google Scholar
  19. 19.
    Schwerdt, K., Crowley, J.: Robust face tracking using colour. In: Proc. Int’l Conf. Auto. Face and Gesture Recognition, pp. 90–95 (2000)Google Scholar
  20. 20.
    Sung, K., Poggio, T.: Example-based learning for view-based face detection. IEEE Trans. PAMI 20, 39–51 (1998)Google Scholar
  21. 21.
    Vapnik, V.: The Nature of Statistical Learning Theory. Springer, Heidelberg (1995)MATHGoogle Scholar
  22. 22.
    Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: IEEE Proc. CVPR (2001)Google Scholar
  23. 23.

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Sachin Gangaputra
    • 1
  • Donald Geman
    • 2
  1. 1.Dept. of Electrical and Computer EngineeringThe Johns Hopkins UniversityBaltimoreUSA
  2. 2.Dept. of Applied Mathematics and StatisticsThe Johns Hopkins UniversityBaltimoreUSA

Personalised recommendations