LABELING HUMAN MOTION SEQUENCES USING GRAPHICAL MODELS

José I. Gómez, Manuel J. Marín-Jiménez, Nicolas Pérez de la Blanca

2009

Abstract

Graphical models have proved to be very efficient models for labeling image data. In particular, they have been used to label data samples from human body images. In this paper, the use of graphical models is studied for human-body landmark localization. Here a new algorithm based on the Branch&Bound methodology, improving the state of the art, is presented. The initialization stage is defined as a local optimum labeling of the sample data. An iterative improvement is given on the labeling space in order to reach new graphs with a lower cost than the current best one. Two branch prune strategies are suggested under a B&B approach in order to speed up the search: a) the use of heuristics; and b) the use of a node dominance criterion. Experimental results on human motion databases show that our proposed algorithm behaves better than the classical Dynamic Programming based approach.

References

  1. Amit, Y. and Kong, A. (1996). Graphical templates for model registration. IEEE PAMI, 18(3):225-236.
  2. Caelli, T. and Caetano, T. S. (2005). Graphical models for graph matching: Approximate models and optimal algorithms. Pattern Recognition Letters, 26(3):339- 346.
  3. Cover, T. and Thomas, J. (1991). Elements of Information Theory. John Wiley and Sons.
  4. Fanti, C., Polito, M., and Perona, P. (2003). An improved scheme for detection and labelling johanson displays. In NIPS.
  5. Fischler, M. A. and Elschlager, R. A. (1973). The representation and matching of pictorial structures. IEEE Trans. Comput., 22(1):67-92.
  6. Fujino, T. and Fujiwara, H. (1994). A method of search space pruning based on search state dominance. Journal of Circuits, Systems and Computers, 25(4):1-12.
  7. Gold, S. and Rangarajan, A. (1996). A graduated assignment algorithm for graph matching. IEEE Trans. Pattern Anal. Mach. Intell., 18(4):377-388.
  8. Grimson, W. E. L. (1990). Object recognition by computer: the role of geometric constraints. MIT Press, Cambridge, MA, USA.
  9. Hansen, E. A., Zilberstein, S., and Danilchenko, V. A. (1997). Anytime heuristic search: First results. Technical Report UM-CS-1997-050.
  10. Haralick, R. M. and Shapiro, L. G. (1992). Computer and Robot Vision. Addison-Wesley Longman Publishing Co., Inc., Boston, MA, USA.
  11. Ibaraki, T. (1977). The power of dominance relations in branch-and-bound algorithms. Journal of ACM, 24(2):264-279.
  12. Rangarajan, A., Chui, H., and Bookstein, F. L. (1997). The softassign procrustes matching algorithm. In IPMI 7897: Proceedings of the 15th International Conference on Information Processing in Medical Imaging, pages 29-42, London, UK. Springer-Verlag.
  13. Sigal, L. and Black, M. (2006). Humaneva: Synchronized video and motion capture dataset for evaluation of articulated human motion. Technical report, Brown University, Department of Computer Science.
  14. Song, Y., Feng, X., and Perona, P. (2000). Towards detection of human motion. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 1:810-817.
  15. Song, Y., Goncalves, L., and Perona, P. (2001). Learning probabilistic structure for human motion detection. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2:771-777.
  16. Song, Y., Goncalves, L., and Perona, P. (2003). Unsupervised learning of human motion. IEEE Trans. Patt. Anal. and Mach. Intell., 25(7):1-14.
  17. Ullman, S. (1996). High-level Vision. MIT Press.
  18. Yu, C. and Wah, B. (1988). Learning dominance relations in combined search problems. IEEE Transactions on Software Engineering, 14(8):1155-1175.
Download


Paper Citation


in Harvard Style

I. Gómez J., J. Marín-Jiménez M. and Pérez de la Blanca N. (2009). LABELING HUMAN MOTION SEQUENCES USING GRAPHICAL MODELS . In Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2009) ISBN 978-989-8111-69-2, pages 488-495. DOI: 10.5220/0001795704880495


in Bibtex Style

@conference{visapp09,
author={José I. Gómez and Manuel J. Marín-Jiménez and Nicolas Pérez de la Blanca},
title={LABELING HUMAN MOTION SEQUENCES USING GRAPHICAL MODELS},
booktitle={Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2009)},
year={2009},
pages={488-495},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001795704880495},
isbn={978-989-8111-69-2},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2009)
TI - LABELING HUMAN MOTION SEQUENCES USING GRAPHICAL MODELS
SN - 978-989-8111-69-2
AU - I. Gómez J.
AU - J. Marín-Jiménez M.
AU - Pérez de la Blanca N.
PY - 2009
SP - 488
EP - 495
DO - 10.5220/0001795704880495