Advertisement

Boosted Multiple Deformable Trees for Parsing Human Poses

  • Yang Wang
  • Greg Mori
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4814)

Abstract

Tree-structured models have been widely used for human pose estimation, in either 2D or 3D. While such models allow efficient learning and inference, they fail to capture additional dependencies between body parts, other than kinematic constraints. In this paper, we consider the use of multiple tree models, rather than a single tree model for human pose estimation. Our model can alleviate the limitations of a single tree-structured model by combining information provided across different tree models. The parameters of each individual tree model are trained via standard learning algorithms in a single tree-structured model. Different tree models are combined in a discriminative fashion by a boosting procedure. We present experimental results showing the improvement of our model over previous approaches on a very challenging dataset.

Keywords

Computer Vision Tree Model Neural Information Processing System Conditional Random Field Weak Learner 
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.
    Crandell, D., Felzenszwalb, P.F., Huttenlocher, D.P.: Spatial priors for part-based recognition using statistical models. In: IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 10–17 (2005)Google Scholar
  2. 2.
    Felzenszwalb, P.F., Huttenlocher, D.P.: Pictorial structures for object recognition. International Journal of Computer Vision 61(1), 55–79 (2003)CrossRefGoogle Scholar
  3. 3.
    Forsyth, D.A., Arikan, O., Ikemoto, L., O’Brien, J., Ramanan, D.: Computational studies of human motion: Part 1, tracking and motion synthesis. Foundations and Trends in Computer Graphics and Vision 1(2/3), 77–254 (2006)CrossRefGoogle Scholar
  4. 4.
    Hogg, D.: Model-based vision: a program to see a walking person. Image and Vision Computing 1(1), 5–20 (1983)CrossRefGoogle Scholar
  5. 5.
    Hua, G., Yang, M.H., Wu, Y.: Learning to estimate human pose with data driven belief propagation. In: IEEE Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 747–754 (2005)Google Scholar
  6. 6.
    Ioffe, S., Forsyth, D.: Finding people by sampling. In: IEEE International Conference on Computer Vision, vol. 2, pp. 1092–1097 (1999)Google Scholar
  7. 7.
    Ju, S.X., Black, M.J., Yaccob, Y.: Cardboard people: A parameterized model of articulated image motion. In: International Conference on Automatic Face and Gesture Recognition, pp. 38–44 (1996)Google Scholar
  8. 8.
    Lafferty, J., McCallum, A., Pereira, F.: Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In: ICML. International Conference on Machine Learning, pp. 282–289 (2001)Google Scholar
  9. 9.
    Lan, X., Huttenlocher, D.P.: Beyond trees: Common-factor models for 2d human pose recovery. In: IEEE International Conference on Computer Vision, vol. 1, pp. 470–477 (2005)Google Scholar
  10. 10.
    Lee, M.W., Cohen, I.: Proposal maps driven mcmc for estimating human body pose in static images. In: IEEE Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 334–341 (2004)Google Scholar
  11. 11.
    Meila, M., Jordan, M.I.: Learing with mixtures of trees. Journal of Machine Learning Research 1, 1–48 (2000)CrossRefMathSciNetGoogle Scholar
  12. 12.
    Mori, G.: Guiding model search using segmentation. In: IEEE International Conference on Computer Vision, vol. 2, pp. 1417–1423 (2005)Google Scholar
  13. 13.
    Mori, G., Malik, J.: Estimating human body configurations using shape context matching. In: European Conference on Computer Vision, vol. 3, pp. 666–680 (2002)Google Scholar
  14. 14.
    Mori, G., Ren, X., Efros, A., Malik, J.: Recovering human body configuration: Combining segmentation and recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 326–333 (2004)Google Scholar
  15. 15.
    Ramanan, D.: Learning to parse images of articulated bodies. In: Advances in Neural Information Processing Systems, vol. 19, pp. 1129–1136 (2007)Google Scholar
  16. 16.
    Ramanan, D., Forsyth, D.A., Zisserman, A.: Strike a pose: Tracking people by finding stylized poses. In: IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 271–278 (2005)Google Scholar
  17. 17.
    Ramanan, D., Sminchisescu, C.: Training deformable models for localization. In: IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 206–213 (2006)Google Scholar
  18. 18.
    Ren, X., Berg, A., Malik, J.: Recovering human body configurations using pairwise constraints between parts. In: IEEE International Conference on Computer Vision, vol. 1, pp. 824–831 (2005)Google Scholar
  19. 19.
    Shakhnarovich, G., Viola, P., Darrell, T.: Fast pose estimation with parameter sensitive hashing. In: IEEE International Conference on Computer Vision, vol. 2, pp. 750–757 (2003)Google Scholar
  20. 20.
    Sigal, L., Black, M.J.: Measure locally, reason globally: Occlusion-sensitive articulated pose estimation. In: IEEE Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 2041–2048 (2006)Google Scholar
  21. 21.
    Song, Y., Goncalves, L., Perona, P.: Unsupervised learning of human motion. IEEE Transaction on Pattern Analysis and Machine Intelligence 25(7), 814–827 (2003)CrossRefGoogle Scholar
  22. 22.
    Srinivasan, P., Shi, J.: Bottom-up recognition and parsing of the human body. In: IEEE Conference on Computer Vision and Pattern Recognition, IEEE Computer Society Press, Los Alamitos (2007)Google Scholar
  23. 23.
    Sudderth, E.B., Mandel, M.I., Freeman, W.T., Willsky, A.S.: Distributed occlusion reasoning for tracking with nonparametric belief propagation. In: Advances in Neural Information Processing Systems, pp. 1369–1376. MIT Press, Cambridge (2004)Google Scholar
  24. 24.
    Sullivan, J., Carlsson, S.: Recognizing and tracking human action. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2352, pp. 629–644. Springer, Heidelberg (2002)Google Scholar
  25. 25.
    Torralba, A., Murphy, K.P., Freeman, W.T.: Contextual models for object detection using boosted random fields. In: Advances in Neural Information Processing Systems, vol. 17, pp. 1401–1408. MIT Press, Cambridge (2005)Google Scholar
  26. 26.
    Toyama, K., Blake, A.: Probabilistic exemplar-based tracking in a metric space. In: IEEE International Conference on Computer Vision, vol. 2, pp. 50–57 (2001)Google Scholar
  27. 27.
    Truyen, T.T., Phung, D.Q., Bui, H.H., Venkatesh, S.: AdaBoost.MRF: Boosted markov random forests and application to multilevel activity recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 1686–1693 (2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Yang Wang
    • 1
  • Greg Mori
    • 1
  1. 1.School of Computing Science, Simon Fraser University, Burnaby, BCCanada

Personalised recommendations