A 3D Shape Descriptor for Human Pose Recovery

  • Laetitia Gond
  • Patrick Sayd
  • Thierry Chateau
  • Michel Dhome
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5098)


This paper deals with human body pose recovery through a multicamera system, which is a key task in monitoring of human activity. The proposed algorithm reconstructs the 3D visual hull of the observed body and characterizes its shape with a new 3D shape descriptor. The body pose is then infered through an original two-stage regression process. As the learning step is independant of the camera configuration, the resulting system is easy to set up. This solution is evaluated on synthetic scenes and promising results on real images are also presented.


Visual Hull Learning Step Voxel Data Voxel Reconstruction Root Joint 
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.
    Cham, T.J., Rehg, J.M.: A multiple hypothesis approach to figure tracking. In: CVPR (1999)Google Scholar
  2. 2.
    Sminchisescu, C., Triggs, B.: Estimating articulated human motion with covariance scaled sampling. I. J. Robotic Res (2003)Google Scholar
  3. 3.
    Shakhnarovich, G., Viola, P., Darrell, T.: Fast pose estimation with parameter-sensitive hashing. In: ICCV (2003)Google Scholar
  4. 4.
    Rosales, R., Sclaroff, S.: Specialized mappings and the estimation of human body pose from a single image. In: HUMO 2000 (2000)Google Scholar
  5. 5.
    Agarwal, A., Triggs, B.: Recovering 3d human pose from monocular images. PAMI (2006)Google Scholar
  6. 6.
    Grauman, K., Shakhnarovich, G., Darrell, T.: Inferring 3d structure with a statistical image-based shape model. In: ICCV (2003)Google Scholar
  7. 7.
    Sun, Y., Bray, M., Thayananthan, A., Yuan, B., Torr, P.: Regression-based human motion capture from voxel data. In: BMVC (2006)Google Scholar
  8. 8.
    Tuzel, O., Porikli, F., Meer, P.: A bayesian approach to background modeling. In: CVPR (2005)Google Scholar
  9. 9.
    Cheung, G.K.M., Kanade, T., Bouguet, J.Y., Holler, M.: A real time system for robust 3d voxel reconstruction of human motions. In: ICCV (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Laetitia Gond
    • 1
  • Patrick Sayd
    • 1
  • Thierry Chateau
    • 2
  • Michel Dhome
    • 2
  1. 1.CEA, LIST, Laboratoire Systèmes de Vision EmbarquésGif-sur-Yvette 
  2. 2.LASMEA CNRSUniversité Blaise PascalClermont-FerrandFrance

Personalised recommendations