Advertisement

Human Pose Estimation from Polluted Silhouettes Using Sub-manifold Voting Strategy

  • Chunfeng Shen
  • Xueyin Lin
  • Yuanchun Shi
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4153)

Abstract

In this paper, we introduce a framework of human pose estimation from polluted silhouettes due to occlusions or shadows. Since the body pose (and configuration) can be estimated by partial components of the silhouette, a robust statistical method is applied to extract useful information from these components. In this method a Gaussian Process model is used to create each sub-manifold corresponding to the component of input data in advance. A sub-manifold voting strategy is then applied to infer the pose structure based on these sub-manifolds. Experiments show that our approach has a great ability to estimate human poses from polluted silhouettes with small computational burden.

Keywords

Latent Variable Input Image IEEE Conf Latent Variable Model Relevance Vector Machine 
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.
    Sminchisescu, C., Triggs, B.: Covariance scaled sampling for monocular 3d body tracking. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 447–454 (2001)Google Scholar
  2. 2.
    Lee, M.W., Cohen, I.: Proposal maps driven mcmc for estimating human body pose in static images. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 2, pp. 334–341 (2004)Google Scholar
  3. 3.
    zhou, H., Huang, T.S.: Okapi-chamfer matching for articulate object recognition. In: Proc. IEEE Int. Conf. Computer Vision, vol. 2, pp. 1026–1033 (2005)Google Scholar
  4. 4.
    Shakhnarovich, G., Viola, P.A., Darrell, T.: Fast pose estimation with parameter-sensitive hashing. In: Proc. IEEE Int. Conf. Computer Vision, vol. 2, pp. 750–759 (2003)Google Scholar
  5. 5.
    Athitsos, V., Sclaroff, S.: Estimating 3d hand pose from a cluttered image. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 2, pp. 432–442 (2003)Google Scholar
  6. 6.
    Agarwal, A., Triggs, B.: 3d human pose from silhouettes by relevance vector regression. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 2, pp. 882–888 (2004)Google Scholar
  7. 7.
    Rosales, R., Athitsos, V., Sigal, L., Sclaroff, S.: 3d hand pose reconstruction using specialized mappings. In: Proc. IEEE Int. Conf. Computer Vision, vol. 1, pp. 378–387 (2001)Google Scholar
  8. 8.
    Elgammal, A.M., Lee, C.S.: Inferring 3d body pose from silhouettes using activity manifold learning. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 2, pp. 681–688 (2004)Google Scholar
  9. 9.
    Grochow, K., Martin, S.L., Hertzmann, A., Popovic, Z.: Style-based inverse kinematics. ACM Trans. Graph. 23(3), 522–531 (2004)CrossRefGoogle Scholar
  10. 10.
    Lawrence, N.D.: Gaussian process latent variable models for visualisation of high dimensional data. In: Proc. NIPs (2003)Google Scholar
  11. 11.
    MacKay, D.: Introduction to gaussian processes. In: Proc. Neural Networks and Machine Learning, pp. 133–165 (1998)Google Scholar
  12. 12.
    Grauman, K., Shakhnarovich, G., Darrell, T.: Inferring 3d structure with a statistical image-based shape model. In: Proc. IEEE Int. Conf. Computer Vision, vol. 1, pp. 641–648 (2003)Google Scholar
  13. 13.
    Chang, C., Ansari, R., Khokhar, A.A.: Cyclic articulated human motion tracking by sequential ancestral simulation. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 2, pp. 45–52 (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Chunfeng Shen
    • 1
  • Xueyin Lin
    • 1
  • Yuanchun Shi
    • 1
  1. 1.Key Lab of Pervasive Computing(MOE), Dept. of Computer Science & TechnologyTsinghua UniversityBeijingP.R. China

Personalised recommendations