Advertisement

Primitive Based Action Representation and Recognition

  • Sanmohan
  • Volker Krüger
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5575)

Abstract

There has been a recent interest in segmenting action sequences into meaningful parts (action primitives) and to model actions on a higher level based on these action primitives. Unlike previous works where action primitives are defined a-priori and search is made for them later, we present a sequential and statistical learning algorithm for automatic detection of the action primitives and the action grammar based on these primitives. We model a set of actions using a single HMM whose structure is learned incrementally as we observe new types. Actions are modeled with sufficient number of Gaussians which would become the states of an HMM for an action. For different actions we find the states that are common in the actions which are then treated as an action primitive.

Keywords

Outgoing Edge Empty String Action Primitive Plan Recognition Surveillance Scenario 
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.

References

  1. 1.
    Barbič, J., Safonova, A., Pan, J.-Y., Faloutsos, C., Hodgins, J.K., Pollard, N.S.: Segmenting motion capture data into distinct behaviors. In: GI 2004: Proceedings of Graphics Interface 2004, School of Computer Science, University of Waterloo, Waterloo, Ontario, Canada, pp. 185–194. Canadian Human-Computer Communications Society (2004)Google Scholar
  2. 2.
    Bizzi, E., Giszter, S.F., Loeb, E., Mussa-Ivaldi, F.A., Saltiel, P.: Modular organization of motor behavior in the frog’s spinal cord. Trends Neurosci. 18(10), 442–446 (1995)CrossRefGoogle Scholar
  3. 3.
    Bobick, A.: Movement, Activity, and Action: The Role of Knowledge in the Perception of Motion. Philosophical Trans. Royal Soc. London 352, 1257–1265 (1997)CrossRefGoogle Scholar
  4. 4.
    Bobick, A.F., Wilson, A.D.: A state-based approach to the representation and recognition of gesture. IEEE Transactions on Pattern Analysis and Machine Intelligence 19(12), 1325–1337 (1997)CrossRefGoogle Scholar
  5. 5.
    Fod, A., Matarić, M.J., Jenkins, O.C.: Automated derivation of primitives for movement classification. Autonomous Robots 12(1), 39–54 (2002)CrossRefzbMATHGoogle Scholar
  6. 6.
    Guerra-Filho, G., Aloimonos, Y.: A sensory-motor language for human activity understanding. In: 2006 6th IEEE-RAS International Conference on Humanoid Robots, December 4-6, 2006, pp. 69–75 (2006)Google Scholar
  7. 7.
    Fermüller, C., Guerra-Filho, G., Aloimonos, Y.: Discovering a language for human activity. In: AAAI 2005 Fall Symposium on Anticipatory Cognitive Embodied Systems, Washington, DC, pp. 70–77 (2005)Google Scholar
  8. 8.
    Hong, P., Turk, M., Huang, T.: Gesture modeling and recognition using finite state machines (2000)Google Scholar
  9. 9.
    Moeslund, T., Hilton, A., Krueger, V.: A survey of advances in vision-based human motion capture and analysis. Computer Vision and Image Understanding 104(2-3), 90–127 (2006)CrossRefGoogle Scholar
  10. 10.
    Rabiner, L.R., Juang, B.H.: Fundamentals of Speech Recognition. Prentice Hall, Englewood Cliffs (1993)zbMATHGoogle Scholar
  11. 11.
    Robertson, N., Reid, I.: Behaviour Understanding in Video: A Combined Method. In: Internatinal Conference on Computer Vision, Beijing, China, October 15-21 (2005)Google Scholar
  12. 12.
    Stauffer, C., Grimson, W.E.L.: Learning Patterns of Activity Using Real-Time Tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence 22(8), 747–757 (2000)CrossRefGoogle Scholar
  13. 13.
    Stolcke, A., Omohundro, S.M.: Best-first model merging for hidden Markov model induction. Technical Report TR-94-003, 1947 Center Street, Berkeley, CA (1994)Google Scholar
  14. 14.
    Vicente, I.S., Kyrki, V., Kragic, D.: Action recognition and understanding through motor primitives. Advanced Robotics 21, 1687–1707 (2007)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Sanmohan
    • 1
  • Volker Krüger
    • 1
  1. 1.Computer Vision and Machine Intelligence LabCopenhagen Institute of TechnologyBallerupDenmark

Personalised recommendations