Modeling Multi-Object Activities in Phase Space

  • Ricky J. Sethi
  • Amit K. Roy-Chowdhury
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6468)


Modeling and recognition of complex activities involving multiple, interacting objects in video is a significant problem in computer vision. In this paper, we examine activities using relative distances in phase space via pairwise analysis of all objects. This allows us to characterize simple interactions directly by modeling multi-object activities with the Multiple Objects, Pairwise Analysis (MOPA) feature vector, which is based upon physical models of multiple interactions in phase space. In this initial formulation, we model paired motion as a damped oscillator in phase space. Experimental validation of the theory is provided on the standard VIVID and UCR Videoweb datasets capturing a variety of problem settings.


Phase Space Relative Distance Activity Recognition Logarithmic Decrement Pairwise Analysis 
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.
    Turaga, P., Chellappa, R., Subrahmanian, V., Udrea, O.: Machine recognition of human activities: A survey. In: CSVT (2008)Google Scholar
  2. 2.
    Ryoo, M., Aggarwal, J.: Spatio-temporal relationship match: Video structure comparison for recognition of complex human activities. In: ICCV (2009)Google Scholar
  3. 3.
    Duchenne, O., Laptev, I., Sivic, J., Bach, F., Ponce, J.: Automatic annotation of human actions in video. In: ICCV (2009)Google Scholar
  4. 4.
    Oliver, N., Rosario, B., Pentland, A.: A bayesian computer vision system for modeling human interactions. In: ICVS (1999)Google Scholar
  5. 5.
    Gaur, U., Song, B., Roy-Chowdhury, A.: Query-based retrieval of complex activities using s̈trings of motion-words.̈ In: WMVC (2009)Google Scholar
  6. 6.
    LeCun, Y., Chopra, S., Ranzato, M., Huang, F.: Energy-based models in document recognition and computer vision. In: ICDAR (2007)Google Scholar
  7. 7.
    Bruhn, A., Weickert, J., Schnorr, C.: Lucas/kanade meets horn/schunck: combining local and global optic flow methods. In: IJCV, pp. 211–231 (2005)Google Scholar
  8. 8.
    Sethi, R., Roy-Chowdhury, A., Ali, S.: Activity recognition by integrating the physics of motion with a neuromorphic model of perception. In: WMVC (2009)Google Scholar
  9. 9.
    Hu, M., Ali, S., Shah, M.: Detecting global motion patterns in complex videos. In: ICPR (2008)Google Scholar
  10. 10.
    Goldstein, H.: Classical Mechanics, 2nd edn. Addison-Wesley, Reading (1980)zbMATHGoogle Scholar
  11. 11.
    Landau, L., Lifshitz, E.: Course of Theoretical Physics: Mechanics, 3rd edn (1976)Google Scholar
  12. 12.
    Marion, J., Thornton, S.: Classical Dynamics of Particles and Systems, 4th edn. Saunders, Philadelphia (1995)Google Scholar
  13. 13.
    Fowles, G., Cassiday, G.: Analytical Mechanics, 6th edn. Brooks Cole, Pacific Grove (2004)Google Scholar
  14. 14.
    Anonymous: A stochastic optimization framework for stable multi-target tracking (2010)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Ricky J. Sethi
    • 1
  • Amit K. Roy-Chowdhury
    • 1
  1. 1.UC RiversideUSA

Personalised recommendations