AUTOMATIC CONSTRUCTION OF HIERARCHICAL HIDDEN MARKOV MODEL STRUCTURE FOR DISCOVERING SEMANTIC PATTERNS IN MOTION DATA

O. Samko, A. D. Marshall, P. L. Rosin

2010

Abstract

The objective of this paper is to automatically build a Hierarchical Hidden Markov Model (HHMM) (Fine et al., 1998) structure to detect semantic patterns from data with an unknown structure by exploring the natural hierarchical decomposition embedded in the data. The problem is important for effective motion data representation and analysis in a variety of applications: film and game making, military, entertainment, sport and medicine. We propose to represent the patterns of the data as an HHMM built utilising a two-stage learning algorithm. The novelty of our method is that it is the first fully automated approach to build an HHMM structure for motion data. Experimental results on different motion features (3D and angular pose coordinates, silhouettes extracted from the video sequence) demonstrate the approach is effective at automatically constructing efficient HHMM with a structure which naturally represents the underlying motion that allows for accurate modelling of the data for applications such as tracking and motion resynthesis.

References

  1. Bengio, Y., Paiement, J., and Vincent, P. (2004). Outof-sample extensions for LLE, Isomap, MDS, Eigenmaps and spectral clustering. Advances in Neural Information Processing Systems 16.
  2. Bowden, R. (2000). Learning non-linear models of shape and motion. PhD Thesis, Dept Systems Engineering, Brunel University.
  3. Choi, H., Nesvizhskii, A., Ghosh, D., and Qin, Z. (2009). Hierarchical HMM with application to joint analysis of ChIP-seq and ChIP-chip data. Bioinformatics, (25):1715-1721.
  4. Duda, R. O., Hart, P. E., and Stork, D. G. (2000). Pattern Classification. Wiley-Interscience Publication.
  5. Fine, S., Singer, Y., and Tishby, N. (1998). The hierarchical hidden markov model: Analysis and applications. Machine Learning, 32(1):41-62.
  6. Hu, M., Ingram, C., Sirski, M., Pal, C., Swamy, S., and Patten, C. (2000). A hierarchical HMM implementation for vertebrate gene splice site prediction. Technical report, Dept. of Computer Science, University of Waterloo.
  7. Junejo, I., Dexter, E., Laptev, I., and Perez, P. (2008). Cross-view action recognition from temporal selfsimilarities. ECCV, pages 293-306.
  8. Kawanaka, D., Okatani, T., and Deguchi, K. (2006). HHMM based recognition of human activity. IEICE Transactions Inf. and Syst., 89(7):2180-2185.
  9. McLachlan, G. and Basford, K. (1988). Mixture models: Inference and applications to clustering. Marcel Dekker.
  10. Murphy, K. and Paskin, M. (2001). Linear time inference in Hierarchical HMMs. Proc. Neural Information Processing Systems.
  11. Nguyen, N. and Venkatesh, S. (2008). Discovery of activity structures using the Hierarchical Hidden Markov Model. BMVC, pages 112-122.
  12. Rosin, P. L. (2001). Unimodal thresholding. Pattern Recognition, 34:2083-2096.
  13. Samko, O., Marshall, A., and Rosin, P. (2006). Selection of the optimal parameter value for the isomap algorithm. Pattern Rocognition Letters, 27:968-979.
  14. Silva, V. and Tenenbaum, J. (2003). Local versus global methods for nonlinear dimensionality reduction. In Advances in Neural Information Processing Systems, volume 15.
  15. Tenenbaum, J., Silva, V., and Langford, J. (2000). A global geometric framework for nonlinear dimensionality reduction. Science, 290:2319-2323.
  16. Xie, L., Chang, S., Divakaran, A., and Sun, H. (2003). Feature selection and order identification for unsupervised discovery of statistical temporal structures in video. IEEE International Conference on Image Processing (ICIP), 1:29-32.
  17. Youngblood, G. M. and Cook, D. J. (2007). Data mining for hierarchical model creation. IEEE Transactions on Systems, Man, and Cybernetics, Part C, 37(4):561- 572.
Download


Paper Citation


in Harvard Style

Samko O., D. Marshall A. and L. Rosin P. (2010). AUTOMATIC CONSTRUCTION OF HIERARCHICAL HIDDEN MARKOV MODEL STRUCTURE FOR DISCOVERING SEMANTIC PATTERNS IN MOTION DATA . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2010) ISBN 978-989-674-028-3, pages 275-280. DOI: 10.5220/0002815202750280


in Bibtex Style

@conference{visapp10,
author={O. Samko and A. D. Marshall and P. L. Rosin},
title={AUTOMATIC CONSTRUCTION OF HIERARCHICAL HIDDEN MARKOV MODEL STRUCTURE FOR DISCOVERING SEMANTIC PATTERNS IN MOTION DATA},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2010)},
year={2010},
pages={275-280},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002815202750280},
isbn={978-989-674-028-3},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2010)
TI - AUTOMATIC CONSTRUCTION OF HIERARCHICAL HIDDEN MARKOV MODEL STRUCTURE FOR DISCOVERING SEMANTIC PATTERNS IN MOTION DATA
SN - 978-989-674-028-3
AU - Samko O.
AU - D. Marshall A.
AU - L. Rosin P.
PY - 2010
SP - 275
EP - 280
DO - 10.5220/0002815202750280