Developing Context Sensitive HMM Gesture Recognition

  • Kingsley Sage
  • A. Jonathan Howell
  • Hilary Buxton
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2915)


We are interested in methods for building cognitive vision systems to understand activities of expert operators for our ActIPret System. Our approach to the gesture recognition required here is to learn the generic models and develop methods for contextual bias of the visual interpretation in the online system. The paper first introduces issues in the development of such flexible and robust gesture learning and recognition, with a brief discussion of related research. Second, the computational model for the Hidden Markov Model (HMM) is described and results with varying amounts of noise in the training and testing phases are given. Third, extensions of this work to allow both top-down bias in the contextual processing and bottom-up augmentation by moment to moment observation of the hand trajectory are described.


Root Mean Square Hide Markov Model Gesture Recognition Hide State Trajectory Data 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Bauer, B., Heinz, H., Kraiss, K.: Video-based continuous sign language recognition using statistical methods. In: IEEE International Conference on Automatic Face and Gesture Recognition, pp. 440–445, Grenoble, France (2000)Google Scholar
  2. 2.
    Black, M.J., Jepson, A.: A probabilistic framework for matching temporal. In: European Conference on Computer Vision, Cambridge, UK, pp. 343–356 (1996)Google Scholar
  3. 3.
    Blei, D.M., Moreno, P.J.: Topic segmentation with an aspect hidden Markov model. In: Proceedings of the 24th International Conference on Research and Development in Information Retrieval (SIGIR 2001), New York, pp. 343–348 (2001)Google Scholar
  4. 4.
    Bobick, A., Davies, J.: The recognition of human movement using temporal templates. IEEE Transactions on Pattern Analysis and Machine Intelligence 23, 257–267 (2001)CrossRefGoogle Scholar
  5. 5.
    Buxton, H., Gong, S.: Visual surveillance in a dynamic and uncertain world. Artificial Intelligence 78, 431–459 (1995)CrossRefGoogle Scholar
  6. 6.
    Buxton, H., Howell, A.J., Sage, K.: The role of task control and context in learning to recognise gesture. In: Cognitive Vision Workshop, Zürich, Switzerland (2002)Google Scholar
  7. 7.
    Dempster, A., Laird, N., Rubin, D.: Maximum likelihood from imcomplete data using the em algorithm. Journal of the Royal Statistical Society 39, 185–197 (1977)MathSciNetGoogle Scholar
  8. 8.
    Gong, S., Buxton, H.: On the visual expectations of moving objects: A probabilistic approach with augmented hidden Markov model. In: European Conference on Artificial Intelligence, Vienna, Austria, pp. 781–785 (1992)Google Scholar
  9. 9.
    Howarth, R., Buxton, H.: Conceptual descriptions from monitoring and watching image sequences. Image and Vision Computing 18, 105–135 (2000)CrossRefGoogle Scholar
  10. 10.
    Howell, A.J., Buxton, H.: Learning gestures for visually mediated interaction. In: British Machine Vision Conference, Southampton, UK, pp. 508–517 (1998)Google Scholar
  11. 11.
    Isard, M., Blake, A.: Contour tracking by stochastic propagation of conditional density. In: Buxton, B.F., Cipolla, R. (eds.) ECCV 1996. LNCS, vol. 1065, pp. 343–356. Springer, Heidelberg (1996)CrossRefGoogle Scholar
  12. 12.
    Johansson, G.: Visual perception of biological motion and a model for its analysis. Perception and Psychophysics 14, 201–211 (1973)CrossRefGoogle Scholar
  13. 13.
    McKenna, S., Gong, S.: Gesture recognition for visually mediated interaction using probabilistic event trajectories. British Machine Vision Association, Southampton, UK (1998)Google Scholar
  14. 14.
    Moore, D.J., Essa, I.A., Hayes, M.H.: Exploiting human actions and object context for recognition tasks. In: IEEE International Conference on Computer Vision, Vancouver, Canada, pp. 80–86 (1999)Google Scholar
  15. 15.
    Rabiner, L.R.: A tutorial on hidden Markov models. Proceedings of the IEEE 77, 257–286 (1989)CrossRefGoogle Scholar
  16. 16.
    Schlenzig, J., Hunter, E., Jain, R.: Recursive indentification of gesture using Hidden Markov Model. In: Workshop on Applications of Computer Vision, Sarasota, Florida (1994)Google Scholar
  17. 17.
    Sherrah, J., Gong, S.: Resolving visual uncertainty and occlusion through probabilistic reasoning. British Machine Vision Association, Bristol, UK (2000)Google Scholar
  18. 18.
    Starner, T., Pentland, A.: Real-time american sign language recognition using hidden Markov models. In: International Symposium on Computer Vision, Coral Gables, FL , pp. 265–270 (1995)Google Scholar
  19. 19.
    Walter, M., Psarrou, A., Gong, S.: Data driven model acquistion using minimum description length. British Machine Vision Association, Manchester, UK (2001)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Kingsley Sage
    • 1
  • A. Jonathan Howell
    • 1
  • Hilary Buxton
    • 1
  1. 1.School of Cognitive and Computing SciencesUniversity of SussexBrightonUK

Personalised recommendations