Using Hidden Markov Models for Recognizing Action Primitives in Complex Actions

  • Volker Krüger
  • Daniel Grest
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4522)


There is biological evidence that human actions are composed out of action primitives, like words and sentences being composed out of phonemes. Similarly to language processing, one possibility to model and recognize complex actions is to use grammars with action primitives as the alphabet. A major challenge here is that the action primitives need to be recovered first from the noisy input signal before further processing with the action grammar can be done. In this paper we combine a Hidden Markov Model-based approach with a simplified version of a condensation algorithm which allows to recover the action primitives in an observed action. In our approach, the primitives may have different lengths, no clear “divider” between the primitives is necessary. The primitive detection is done online, no storing of past data is required. We verify our approach on a large database. Recognition rates are slightly lower than the rate when recognizing the singular action primitives.


Hide Markov Model Speech Recognition Humanoid Robot Motion Primitive Action Primitive 
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.


  1. 1.
    Billard, A., Epars, Y., Calinon, S., Schaal, S., Cheng, G.: Discovering Optimal Imitation Strategies. Robotics and Autonomous Systems 47, 69–77 (2004)CrossRefGoogle Scholar
  2. 2.
    Bobick, A.F.: Movements, Activity, and Action: The Role of Knowledge in the Perception of Motion. In: Royal Society Workshop on Knowledge-based Vision in Man and Machine, London, England (February 1997)Google Scholar
  3. 3.
    Bourlard, H., Morgan, N.: Connectionist Speech Recognition: a Hybrid Approach. Kluwer Academic Publishers, Dordrecht (1994)Google Scholar
  4. 4.
    Calinon, S., Billard, A.: Stochastic Gesture Production and Recognition Model for a Humanoid Robot. In: International Conference on Intelligent Robots and Systems, Alberta, Canada, August 2-6 (2005)Google Scholar
  5. 5.
    Calinon, S., Guenter, F., Billard, A.: Goal-Directed Imitation in a Humanoid Robot. In: International Conference on Robotics and Automation, Barcelona, Spain, April 18-22 (2005)Google Scholar
  6. 6.
    Dariush, B.: Human Motion Analysis for Biomechanics and Biomedicine. Machine Vision and Applications 14, 202–205 (2003)CrossRefGoogle Scholar
  7. 7.
    Giese, M., Poggio, T.: Neural Mechanisms for the Recognition of Biological Movements. Nature Reviews 4, 179–192 (2003)CrossRefGoogle Scholar
  8. 8.
    Hermansky, H.: Perceptual linear predictive (plp) analysis of speech. Journal of Acoustical Society of America 87(4), 1725–1738 (1990)CrossRefGoogle Scholar
  9. 9.
    Huang, X.D., Ariki, Y., Jack, M.A.: Hidden Markov Models for Speech Recognition. Edinburgh University Press, Edinburgh (1990)Google Scholar
  10. 10.
    Huang, X.D., Jack, M.A.: Semi-continous hidden markov models for speech signals. Computer Speech and Language 3, 239–252 (1989)CrossRefGoogle Scholar
  11. 11.
    Ijspeert, A.J., Nakanishi, J., Schaal, S.: Movement Imitation withNonlinear Dynamical Systems in Humanoid Robots. In: International Conference on Robotics and Automation, Washington, DC, USA (2002)Google Scholar
  12. 12.
    Ivanov, Y., Bobick, A.: Recognition of Visual Activities and Interactions by Stochastic Parsing. IEEE Transactions on Pattern Analysis and Machine Intelligence 22(8), 852–872 (2000)CrossRefGoogle Scholar
  13. 13.
    Jenkins, O.C., Mataric, M.: Deriving Action and Behavior Primitives from Human Motion Capture Data. In: International Conference on Robotics and Automation, Washington, DC, USA (2002)Google Scholar
  14. 14.
    Jenkins, O.C., Mataric, M.J.: Deriving Action and Behavior Primitives from Human Motion Data. In: International Conference on Intelligent Robots and Systems, Lausanne, Switzerland, September 30 - October 4, 2002, pp. 2551–2556 (2002)Google Scholar
  15. 15.
    Krueger, V., Anderson, J., Prehn, T.: Probabilistic model-based background subtraction. In: Scandinavian Conference on Image Analysis, Joensuu, Finland, June 19-22, 2005, pp. 180–187 (2005)Google Scholar
  16. 16.
    Lu, C., Ferrier, N.: Repetitive Motion Analysis: Segmentation and Event Classification. IEEE Transactions on Pattern Analysis and Machine Intelligence 26(2), 258–263 (2004)CrossRefGoogle Scholar
  17. 17.
    Nagel, H.-H.: From Image Sequences Towards Conceptual Descriptions. Image and Vision Computing 6(2), 59–74 (1988)CrossRefGoogle Scholar
  18. 18.
    Rabiner, L.R., Juang, B.H.: An introduction to hidden Markov models. IEEE ASSP Magazine, 4–15 (1986)Google Scholar
  19. 19.
    Reng, L., Moeslund, T.B., Granum, E.: Finding Motion Primitives in Human Body Gestures. In: Gibet, S., Courty, N., Kamp, J.-F. (eds.) GW 2005. LNCS (LNAI), vol. 3881, pp. 133–144. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  20. 20.
    Rizzolatti, G., Fogassi, L., Gallese, V.: Parietal Cortex: from Sight to Action. Current Opinion in Neurobiology 7, 562–567 (1997)CrossRefGoogle Scholar
  21. 21.
    Rizzolatti, G., Fogassi, L., Gallese, V.: Neurophysiological Mechanisms Underlying the Understanding and Imitation of Action. Nature Reviews 2, 661–670 (2001)CrossRefGoogle Scholar
  22. 22.
    Schaal, S.: Is Imitation Learning the Route to Humanoid Robots? Trends in Cognitive Sciences 3(6), 233–242 (1999)CrossRefGoogle Scholar
  23. 23.
    Stolcke, A.: An Efficient Probabilistic Context-Free Parsing Algorithm That Computes Prefix Probabilities. Computational Linguistics 21(2), 165–201 (1995)MathSciNetGoogle Scholar

Copyright information

© Springer Berlin Heidelberg 2007

Authors and Affiliations

  • Volker Krüger
    • 1
  • Daniel Grest
    • 1
  1. 1.Computer Vision and Machine Intelligence Lab, CIT, Aalborg University, Lautrupvang 15, 2750 BallerupDenmark

Personalised recommendations