Inferring 3D Body Pose from Uncalibrated Video

  • Xian-Jie Qiu
  • Zhao-Qi Wang
  • Shi-Hong Xia
  • Yong-Chao Sun
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4020)

Abstract

Recovery of 3D body pose is a fundamental problem for human motion analysis in many applications such as motion capture, vision interface, visual surveillance, and gesture recognition. In this paper, we present a new image-based approach to infer 3D human structure parameters from uncalibrated video. The estimation is example based. First, we acquire a special motion database through an off-line motion capture process. Second, given uncalibrated motion video, we abstract the extrinsic parameters and then silhouettes database associated with 3D poses is built by projecting each data of the 3D motion database into 2D plane with the extrinsic parameters. Next, with the image silhouettes abstracted from video, the unknown structure parameters are inferred by performs a similarity search in the database of silhouettes using approach based on shape matching. That is, the 3D structure parameters whose 2D projective silhouette is the most similar to the 2D image silhouette are took as the 3D reconstruction structure. We use trampoline sport motion, an example of complex human motion, to demonstrate the effectiveness of our approach.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Rehg, J.M., Kanade, T.: Model-based tracking of self-occluding articulated objects. In: ICCV, pp. 612–617 (1995)Google Scholar
  2. 2.
    Gavrila, D., Davis, L.: 3-D model-based tracking of humans in action: a multi-view approach. In: IEEE Conference on Computer Vision and Pattern Recognition (1996)Google Scholar
  3. 3.
    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
  4. 4.
    Brand, M.: Shadow puppetry. In: International Conference on Computer Vision, vol. 2, p. 1237 (1999)Google Scholar
  5. 5.
    Grauman, T.D.K., Shakhnarovich, G.: Inferring 3D structure with a statistical image-based shape model. In: ICCV (2003)Google Scholar
  6. 6.
    Howe, L., Freeman, W.: Bayesian reconstruction of 3D human motion from single-camera video. In: Proc. NIPS (1999)Google Scholar
  7. 7.
    Mori, G., Malik, J.: Estimating human body configurations using shape context matching. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2352, pp. 666–680. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  8. 8.
    Shakhnarovich, G., Viola, P., Darrell, T.: Fast pose estimation with parameter-sensitive hashing. In: ICCV (2003)Google Scholar
  9. 9.
    Sminchisescu, C., Triggs, B.: A Robust Multiple Hypothesis Approach to Monocular Human Motion Tracking, research report INRIA-RR-4208 (June 2001)Google Scholar
  10. 10.
    Deutscher, J., Blake, A., Reid, I.: Articulated Body Motion Capture by Annealed Particle Filtering. In: Proc. CVPR, vol. 2, pp. 126–133 (2000)Google Scholar
  11. 11.
    Sminchisescu, C., Triggs, B.: Covariance-Scaled Sampling for Monocular3D Body Tracking. In: Proc. CVPR, pp. 447–454 (2001)Google Scholar
  12. 12.
    Bregler, C., Malik, J.: Tracking People with Twists and Exponential Maps. In: Proc. CVPR (1998)Google Scholar
  13. 13.
    Xian-jie, Q., Zhao-qi, W., Shi-hong, X.: A novel computer vision technique used on sport video. Journal of WSCG, 545–554 (2004)Google Scholar
  14. 14.
    Xian-jie, Q., Zhao-qi, W., Shi-hong, X., Yong-dong, W.: A Virtual-Real Comparison Technique Used on Sport Simulation and Analysis. Journal of Computer Research and Development (in Chinese) (accepted)Google Scholar
  15. 15.
    Sminchisescu, C., Telea, A.: Human Pose Estimation From Silhouettes: A Consistent Approach Using Distance Level Sets. In: The Proceedings of WSCG 2002, Prague, Czech Republic (2002)Google Scholar
  16. 16.
    Hu, M.K.: Visual Pattern Recognition by Moment Invariants. IRE Trans IT- 8, 179–182 (1962)Google Scholar
  17. 17.
    Tomas, F.J.S.: Affine moment invariants: A new tool for character recognition. Pattern recognition Letters 15, 433–436 (1994)CrossRefGoogle Scholar
  18. 18.
    Matusik, W., Buehler, C., Raskar, R., Gortler, S., McMillan, L.: Image-Based Visual Hulls. In: Proceedings ACM Conference on Computer Graphics and Interactive Techniques, pp. 369–374 (2000)Google Scholar
  19. 19.
    Egisys Co.Curious Labs.Poser5: The Ultimate 3D Character Solution (2002)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Xian-Jie Qiu
    • 1
    • 2
  • Zhao-Qi Wang
    • 1
  • Shi-Hong Xia
    • 1
  • Yong-Chao Sun
    • 1
    • 3
  1. 1.Institute of Computing TechnologyThe Chinese Academy of SciencesBeijingChina
  2. 2.Graduate SchoolThe Chinese Academy of SciencesBeijingChina
  3. 3.Institute of Computing TechnologyThe Chinese Academy of SciencesShenyangChina

Personalised recommendations