Advertisement

Integration of Local Image Cues for Probabilistic 2D Pose Recovery

  • Paul Kuo
  • Dimitrios Makris
  • Najla Megherbi
  • Jean-Christophe Nebel
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5359)

Abstract

A novel probabilistic formulation for 2-D human pose recovery from monocular images is proposed. It relies on a bottom-up approach based on an iterative process between clustering and body model fitting. Body parts are segmented from the foreground by clustering a set of images cues. Clustering is driven by 2D human body model fitting to obtain optimal segmentation while the model is resized and its articulated configuration is updated according to the clustering result. This method neither requires a training stage, nor any prior knowledge of poses and appearance as characteristics of body parts are already embedded in the integrated cues. Furthermore, a probabilistic confidence measure is proposed to evaluate the expected accuracy of recovered poses. Experimental results demonstrate the accuracy and robustness of this new algorithm by estimating 2-D human poses from walking sequences.

Keywords

Body Part Body Model Confidence Measure Foreground Pixel Human Body Model 
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.
    Elgammal, A., Lee, C.S.: Inferring 3D body pose from silhouettes using activity manifold Learning. In: CVPR (2), pp. 681–688 (2004)Google Scholar
  2. 2.
    Spencer, N., Carter, J.: Towards pose invariant gait reconstruction ICIP (2), pp. 261–264 (2005)Google Scholar
  3. 3.
    Kuo, P., Nebel, J.-C., Makris, D.: Camera Auto-Calibration from Articulated Motion AVSS, pp. 135–140 (2007)Google Scholar
  4. 4.
    Armstrong, M., Zisserman, A., Hartley, R.: Self-Calibration from image triplets. In: Buxton, B.F., Cipolla, R. (eds.) ECCV 1996. LNCS, vol. 1064, pp. 1–16. Springer, Heidelberg (1996)CrossRefGoogle Scholar
  5. 5.
    Gavrila, D.M.: The visual analysis of human movement: A survey. Journal of computer Vision and Image Understanding 73(1), 82–98 (1999)CrossRefzbMATHGoogle Scholar
  6. 6.
    Srinivasan, P., Shi, J.: Bottom-up recognition and parsing of the human body CVPR, pp. 1–8 (2007)Google Scholar
  7. 7.
    Ren, X., Berg, A.C., Malik, J.: Recovering human body configurations using pairwise constraints. In: ICCV, pp. 824–831 (2005)Google Scholar
  8. 8.
    Ramanan, D., Forsyth, D.A.: Finding and traking people from the bottom up CVPR (2), pp. 467–474 (2003)Google Scholar
  9. 9.
    Mori, G., Ren, X., Efros, A.A., Malik, J. (eds.): Recovering human body configurations: Combing segmentation and recognition CVPR (2), pp. 326–333 (2004)Google Scholar
  10. 10.
    Sigal, L., Black, M.J.: Predicting 3D people from 2D pictures. In: AMDO (2006)Google Scholar
  11. 11.
    Wang, Y., Mori, G.: Boosted multiple deformable trees for parsing human poses. In: HUMO, pp. 16–27 (2007)Google Scholar
  12. 12.
    Hua, G., Yang, M.H., Wu, Y.: Learning to estimate human poses with data driven belief propagation. In: CVPR (2), pp. 747–754 (2005)Google Scholar
  13. 13.
    Felzenszwalb, P., Huttenlocher, D.: Pictorial structures for object recognition. In: IJCV, pp. 55–79 (2005)Google Scholar
  14. 14.
    Ramanan, D.: Learning to parse images of articulated bodies. In: NIPS (2007)Google Scholar
  15. 15.
    Sigal, L., Black, M.J.: Measure locally, reason globally: Occlusion-sensitive articulated pose estimation. In: CVPR (2), pp. 2041–2048 (2006)Google Scholar
  16. 16.
    Yang, H.D., Lee, S.W.: Reconstructing 3D human body pose from stereo image sequences using hierarchical human body model learning. In: ICPR (3), pp. 1004–1007 (2006)Google Scholar
  17. 17.
    Ramanan, D., Forsyth, D.A., Zisserman, A.: Strike a pose: Tracking people by finding stylized poses. In: CVPR (1), pp. 271–278 (2006)Google Scholar
  18. 18.
    Lucas, B.D., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: Imaging understanding workshop, pp. 121–130 (1981)Google Scholar
  19. 19.
    Hartigan, J.A., Wong, M.A.: A K-means clustering algorithm. Applied Statistics 28(1), 100–108 (1979)CrossRefzbMATHGoogle Scholar
  20. 20.
    Da Vinci, L.: Description of "Vitruvian Man" 1492Google Scholar
  21. 21.
    Zhao, T., Nevatia, R.: Bayesian human segmentation in crowded situations. In: CVPR (2), pp. 459–466 (2003)Google Scholar
  22. 22.
    Hu, C., Ma, X., Dai, X.: A Robust person tracking and following approach for mobile robot. In: International Conf. on Mechatronics and Automation, pp. 3571–3576 (2007) Google Scholar
  23. 23.
    Fritsch, J., Kleinehagenbrock, M., Lang, S., Fink, G.A., Sagerer, G.: Audiovisual person tracking with a mobile robot. In: IAS, pp. 898–906 (2004)Google Scholar
  24. 24.
    Mckenna, S.J., Raja, Y., Gong, S.: Tracking colour objects using adaptive mixture models. Image and Vision Computing (17), 231–255 (1999)Google Scholar
  25. 25.
    Martinez-del-Rincon, J., Nebel, J.-C., Makris, D., Orrite, C.: Tracking Human Body Parts Using Particle Filters Constrained by Human Biomechanics. In: BMVC 2008 (2008)Google Scholar
  26. 26.
    HumanEVA dataset. Brown University, http://vision.cs.brown.edu/humaneva
  27. 27.
    Sigal, L., Black, M.J.: HumanEva: Synchronized video and motion capture dataset for evaluation of articulated human motion, Tech. Report CS0608, Brown Univ. (2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Paul Kuo
    • 1
  • Dimitrios Makris
    • 1
  • Najla Megherbi
    • 2
  • Jean-Christophe Nebel
    • 1
  1. 1.Digital Imaging Research CentreKingston UniversityLondonUK
  2. 2.Applied Mathematics and Computing GroupCranfield UniversityUK

Personalised recommendations