Monocular Tracking with a Mixture of View-Dependent Learned Models

  • Tobias Jaeggli
  • Esther Koller-Meier
  • Luc Van Gool
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4069)


This paper considers the problem of monocular human body tracking using learned models. We propose to learn the joint probability distribution of appearance and body pose using a mixture of view-dependent models. In such a way the multimodal and nonlinear relationships can be captured reliably. We formulate inference algorithms that are based on generative models while exploiting the advantages of a learned model when compared to the traditionally used geometric body models. Given static images or sequences, body poses and bounding box locations are inferred using silhouette based image descriptors. Prior information about likely body poses and a motion model are taken into account. We consider analytical computations and Monte-Carlo techniques, as well as a combination of both. In a Rao-Blackwellised particle filter, the tracking problem is partitioned into a part that is solved analytically, and a part that is solved with particle filtering. Tracking results are reported for human locomotion.


Gaussian Mixture Model Tracking Problem Image Descriptor Global Orientation Human Locomotion 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Deutscher, J., Blake, A., Reid, I.: Articulated body motion capture by annealed particle filtering. In: Proc. IEEE CVPR (2000)Google Scholar
  2. 2.
    Sidenbladh, H., Black, M.J., Fleet, D.J.: Stochastic tracking of 3D human figures using 2D image motion. In: Vernon, D. (ed.) ECCV 2000. LNCS, vol. 1843, pp. 702–718. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  3. 3.
    Sigal, L., Bhatia, S., Roth, S., Black, M., Isard, M.: Tracking loose-limbed people. In: CVPR (2004)Google Scholar
  4. 4.
    Sminchisescu, C., Triggs, B.: Kinematic jump processes for monocular 3d human tracking. In: CVPR (2003)Google Scholar
  5. 5.
    Urtasun, R., Fua, P.: 3D human body tracking using deterministic temporal motion models. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3023, pp. 92–106. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  6. 6.
    Shakhnarovich, G., Viola, P., Darrel, T.: Fast pose estimation with parameter sensitive hashing. In: ICCV (2003)Google Scholar
  7. 7.
    Agarwal, A., Triggs, B.: 3d human pose from silhouettes by relevance vector regression. In: CVPR (2004)Google Scholar
  8. 8.
    Agarwal, A., Triggs, B.: Monocular human motion capture with a mixture of regressors. In: IEEE Workshop on Vision for Human-Computer Interaction at CVPR (2005)Google Scholar
  9. 9.
    Elgammal, A., Lee, C.S.: Inferring 3d body pose from silhouettes using activity manifold learning. In: CVPR (2004)Google Scholar
  10. 10.
    Grauman, K., Shakhnarovich, G., Darrel, T.: Inferring 3d structure with a statistical image-based shape model. In: ICCV (2003)Google Scholar
  11. 11.
    Sminchisescu, C., Kanaujia, A., Li, Z., Metaxas, D.: Discriminative density propagation for 3d human motion estimation. In: CVPR (2005)Google Scholar
  12. 12.
    Rosales, R., Sclaroff, S.: Learning body pose via specialized maps. In: Advances in Neural Information Processing Systems (2001)Google Scholar
  13. 13.
    Murphy, K., Russel, S.: Rao-blackwellized particle filtering for dynamic bayesian networks. In: Doucet, A., de Freitas, N., Gordon, N. (eds.) Sequential Monte Carlo Methods in Practice, pp. 499–515. Springer, Heidelberg (2001)Google Scholar
  14. 14.
    Bailey, D.G.: An efficient euclidean distance transform. In: Klette, R., Žunić, J. (eds.) IWCIA 2004. LNCS, vol. 3322, pp. 394–408. Springer, Heidelberg (2004)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Tobias Jaeggli
    • 1
  • Esther Koller-Meier
    • 1
  • Luc Van Gool
    • 1
    • 2
  1. 1.D-ITET/BIWIETH ZurichZurich
  2. 2.ESAT/VISICSKatholieke Universiteit LeuvenLeuven

Personalised recommendations