Stochastic Tracking of 3D Human Figures Using 2D Image Motion

  • Hedvig Sidenbladh
  • Michael J. Black
  • David J. Fleet
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1843)


A probabilistic method for tracking 3D articulated human figures in monocular image sequences is presented. Within a Bayesian framework, we define a generative model of image appearance, a robust likelihood function based on image graylevel differences, and a prior probability distribution over pose and joint angles that models how humans move. The posterior probability distribution over model parameters is represented using a discrete set of samples and is propagated over time using particle filtering. The approach extends previous work on parameterized optical flow estimation to exploit a complex 3D articulated motion model. It also extends previous work on human motion tracking by including a perspective camera model, by modeling limb self occlusion, and by recovering 3D motion from a monocular sequence. The explicit posterior probability distribution represents ambiguities due to image matching, model singularities, and perspective projection. The method relies only on a frame-to-frame assumption of brightness constancy and hence is able to track people under changing viewpoints, in grayscale image sequences, and with complex unknown backgrounds.


Joint Angle Image Motion Perspective Projection Posterior Probability Distribution Prior Probability 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.


  1. 1.
    M. J. Black. Explaining optical flow events with parameterized spatio-temporal models. CVPR, pp. 326–332, 1999.Google Scholar
  2. 2.
    M. J. Black and D. J. Fleet. Probabilistic detection and tracking of motion discontinuities. ICCV, pp. 551–558, 1999.Google Scholar
  3. 3.
    A. Bobick and J. Davis. An appearance-based representation of action. ICPR, 1996.Google Scholar
  4. 4.
    M. Brand. Shadow puppetry. ICCV, pp. 1237–1244, 1999.Google Scholar
  5. 5.
    C. Bregler and J. Malik. Tracking people with twists and exponential maps. CVPR, 1998.Google Scholar
  6. 6.
    T-J. Cham and J. M. Rehg. A multiple hypothesis approach to figure tracking. CVPR, pp. 239–245, 1999.Google Scholar
  7. 7.
    J. Deutscher, B. North, B. Bascle, and A. Blake. Tracking through singularities and discontinuities by random sampling. ICCV, pp. 1144–1149, 1999.Google Scholar
  8. 8.
    D. M. Gavrila. The visual analysis of human movement: a survey. CVIU, 73(1):82–98, 1999.zbMATHGoogle Scholar
  9. 9.
    D. M. Gavrila and L. S. Davis. 3-D model-based tracking of humans in action: A multi-view approach. CVPR, pp. 73–80, 1996.Google Scholar
  10. 10.
    L. Goncalves, E. Di Bernardi, E. Ursella, and P. Perona. Monocular tracking of the human arm in 3D. ICCV, 1995.Google Scholar
  11. 11.
    N. Gordon, D. J. Salmond, and A. F. M. Smith. A novel approach to nonlinear/non-Gaussian Bayesian state estimation. IEE Proc. Radar, Sonar and Navigation, 140(2):107–113, 1996.Google Scholar
  12. 12.
    D. Hogg. Model-based vision: A program to see a walking person. Image and Vision Computing, 1(1):5–20, 1983.CrossRefGoogle Scholar
  13. 13.
    M. Isard and A. Blake. Contour tracking by stochastic propagation of conditional density. ECCV, pp. 343–356, 1996.Google Scholar
  14. 14.
    S. X. Ju, M. J. Black, and Y. Yacoob. Cardboard people: A parameterized model of articulated motion. Int. Conf. on Automatic Face and Gesture Recognition, pp. 38–44, 1996.Google Scholar
  15. 15.
    I. Kakadiaris and D. Metaxas. Model-based estimation of 3D human motion with occlusion based on active multi-viewpoint selection. CVPR, pp. 81–87, 1996.Google Scholar
  16. 16.
    M. E. Leventon and W. T. Freeman. Bayesian estimation of 3-d human motion from an image sequence. TR-98-06, Mitsubishi Electric Research Lab, 1998.Google Scholar
  17. 17.
    D. Morris and J. M. Rehg. Singularity analysis for articulated object tracking. CVPR, pp. 289–296, 1998.Google Scholar
  18. 18.
    V. Pavolvić, J. Rehg, T-J. Cham, and K. Murphy. A dynamic Bayesian network approach to figure tracking using learned dynamic models. ICCV, pp. 94–101, 1999.Google Scholar
  19. 19.
    J. O. Ramsay and B. W. Silverman. Functional data analysis. New York: Springer Verlag, 1997.zbMATHGoogle Scholar
  20. 20.
    H. Sidenbladh, F. de la Torre, and M. J. Black. A framework for modeling the appearance of 3D articulated figures. Int. Conf. on Automatic Face and Gesture Recognition, 2000.Google Scholar
  21. 21.
    S. Wachter and H. H. Nagel. Tracking persons in monocular image sequences. CVIU, 74(3):174–192, 1999.Google Scholar
  22. 22.
    C. Wren, A. Azarbayejani, T. Darrell, and A. Pentland. Pfinder: Real-time tracking of the human body. PAMI, 19(7):780–785, 1997.Google Scholar
  23. 23.
    Y. Yacoob and M. J. Black. Parameterized modeling and recognition of activities in temporal surfaces. CVIU, 73(2):232–247, 1999.Google Scholar
  24. 24.
    Y. Yacoob and L. Davis. Learned temporal models of image motion. ICCV, pp. 446–453, 1998.Google Scholar
  25. 25.
    M. Yamamoto, A. Sato, S. Kawada, T. Kondo, and Y. Osaki. Incremental tracking of human actions from multiple views. CVPR, pp. 2–7, 1998.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2000

Authors and Affiliations

  • Hedvig Sidenbladh
    • 1
  • Michael J. Black
    • 2
  • David J. Fleet
    • 2
  1. 1.CVAP/NADARoyal Institute of Technology (KTHStockholmSweden
  2. 2.Xerox Palo Alto Research CenterPalo AltoUSA

Personalised recommendations