Advertisement

Single-Frame 3D Human Pose Recovery from Multiple Views

  • Michael Hofmann
  • Dariu M. Gavrila
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5748)

Abstract

We present a system for the estimation of unconstrained 3D human upper body pose from multi-camera single-frame views. Pose recovery starts with a shape detection stage where candidate poses are generated based on hierarchical exemplar matching in the individual camera views. The hierarchy used in this stage is created using a hybrid clustering approach in order to efficiently deal with the large number of represented poses. In the following multi-view verification stage, poses are re-projected to the other camera views and ranked according to a multi-view matching score. A subsequent gradient-based local pose optimization stage bridges the gap between the used discrete pose exemplars and the underlying continuous parameter space. We demonstrate that the proposed clustering approach greatly outperforms state-of-the-art bottom-up clustering in parameter space and present a detailed experimental evaluation of the complete system on a large data set.

Keywords

Camera View World Coordinate System Correct Hypothesis Foreground Segmentation Shape Detection 
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.
    Forsyth, D., et al.: Computational studies of human motion. Found. Trends. Comput. Graph. Vis. 1(2-3), 77–254 (2005)CrossRefGoogle Scholar
  2. 2.
    Moeslund, T.B., et al.: A survey of advances in vision-based human motion capture and analysis. CVIU 103(2-3), 90–126 (2006)Google Scholar
  3. 3.
    Cheung, K.M.G., et al.: Shape-from-silhouette across time - parts I and II. IJCV 62 and 63(3), 221–247 and 225–245 (2005)CrossRefGoogle Scholar
  4. 4.
    Mikic, I., et al.: Human body model acquisition and tracking using voxel data. IJCV 53(3), 199–223 (2003)CrossRefGoogle Scholar
  5. 5.
    Starck, J., Hilton, A.: Model-based multiple view reconstruction of people. In: ICCV, pp. 915–922 (2003)Google Scholar
  6. 6.
    Agarwal, A., Triggs, B.: Recovering 3D human pose from monoc. images. TPAMI 28(1), 44–58 (2006)CrossRefGoogle Scholar
  7. 7.
    Bissacco, A., et al.: Fast human pose estimation using appearance and motion via multi-dimensional boosting regression. In: CVPR (2007)Google Scholar
  8. 8.
    Kanaujia, A., et al.: Semi-supervised hierarchical models for 3d human pose reconstruction. In: CVPR (2007)Google Scholar
  9. 9.
    Shakhnarovich, G., et al.: Fast pose estimation with parameter-sensitive hashing. In: ICCV, pp. 750–757 (2003)Google Scholar
  10. 10.
    Kohli, P., et al.: Simultaneous segmentation and pose estimation of humans using dynamic graph cuts. IJCV 79, 285–298 (2008)CrossRefGoogle Scholar
  11. 11.
    Lee, M.W., Cohen, I.: A model-based approach for estimating human 3D poses in static images. TPAMI 28(6), 905–916 (2006)CrossRefGoogle Scholar
  12. 12.
    Mori, G., Malik, J.: Recovering 3D human body configurations using shape contexts. TPAMI 28(7), 1052–1062 (2006)CrossRefGoogle Scholar
  13. 13.
    Ramanan, D., et al.: Tracking people by learning their appearance. TPAMI 29(1), 65–81 (2007)CrossRefGoogle Scholar
  14. 14.
    Sigal, L., et al.: Tracking loose-limbed people. In: CVPR (2004)Google Scholar
  15. 15.
    Navaratnam, R., et al.: Hierarchical part-based human body pose estimation. In: BMVC (2005)Google Scholar
  16. 16.
    Stenger, B., et al.: Model-based hand tracking using a hierarchical Bayesian filter. TPAMI 28(9), 1372–1384 (2006)CrossRefGoogle Scholar
  17. 17.
    Hofmann, M., Gavrila, D.M.: Multi-view 3d human pose estimation combining single-frame recovery, temporal integration and model adaptation. In: CVPR (2009)Google Scholar
  18. 18.
    Gavrila, D.M., Davis, L.: 3-D model-based tracking of humans in action: a multi-view approach. In: CVPR (1996)Google Scholar
  19. 19.
    Zivkovic, Z.: Improved adaptive Gaussian mixture model for background subtraction. In: ICPR (2), pp. 28–31 (2004)Google Scholar
  20. 20.
    Laurentini, A.: The visual hull concept for silhouette-based image understanding. TPAMI 16(2), 150–162 (1994)CrossRefGoogle Scholar
  21. 21.
    Gavrila, D.M., Philomin, V.: Real-time object detection for “smart” vehicles. In: ICCV, pp. 87–93 (1999)Google Scholar
  22. 22.
    Rogez, G., et al.: Randomized trees for human pose detection. In: CVPR (2008)Google Scholar
  23. 23.
    Athitsos, V., Sclaroff, S.: Estimating 3D hand pose from a cluttered image. In: CVPR, pp. II.432–II.439 (2003)Google Scholar
  24. 24.
    Bouguet, J.Y.: Camera calib. toolbox for matlab (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Michael Hofmann
    • 1
  • Dariu M. Gavrila
    • 2
  1. 1.TNO Defence, Security and SafetyThe Netherlands
  2. 2.Intelligent Systems Laboratory, Faculty of ScienceUniversity of AmsterdamThe Netherlands

Personalised recommendations