Abstract
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.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Turaga, P., Chellappa, R., Subrahmanian, V., Udrea, O.: Machine recognition of human activities: A survey. In: CSVT (2008)
Ryoo, M., Aggarwal, J.: Spatio-temporal relationship match: Video structure comparison for recognition of complex human activities. In: ICCV (2009)
Duchenne, O., Laptev, I., Sivic, J., Bach, F., Ponce, J.: Automatic annotation of human actions in video. In: ICCV (2009)
Oliver, N., Rosario, B., Pentland, A.: A bayesian computer vision system for modeling human interactions. In: ICVS (1999)
Gaur, U., Song, B., Roy-Chowdhury, A.: Query-based retrieval of complex activities using s̈trings of motion-words.̈ In: WMVC (2009)
LeCun, Y., Chopra, S., Ranzato, M., Huang, F.: Energy-based models in document recognition and computer vision. In: ICDAR (2007)
Bruhn, A., Weickert, J., Schnorr, C.: Lucas/kanade meets horn/schunck: combining local and global optic flow methods. In: IJCV, pp. 211–231 (2005)
Sethi, R., Roy-Chowdhury, A., Ali, S.: Activity recognition by integrating the physics of motion with a neuromorphic model of perception. In: WMVC (2009)
Hu, M., Ali, S., Shah, M.: Detecting global motion patterns in complex videos. In: ICPR (2008)
Goldstein, H.: Classical Mechanics, 2nd edn. Addison-Wesley, Reading (1980)
Landau, L., Lifshitz, E.: Course of Theoretical Physics: Mechanics, 3rd edn (1976)
Marion, J., Thornton, S.: Classical Dynamics of Particles and Systems, 4th edn. Saunders, Philadelphia (1995)
Fowles, G., Cassiday, G.: Analytical Mechanics, 6th edn. Brooks Cole, Pacific Grove (2004)
Anonymous: A stochastic optimization framework for stable multi-target tracking (2010)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Sethi, R.J., Roy-Chowdhury, A.K. (2011). Modeling Multi-Object Activities in Phase Space. In: Koch, R., Huang, F. (eds) Computer Vision – ACCV 2010 Workshops. ACCV 2010. Lecture Notes in Computer Science, vol 6468. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-22822-3_33
Download citation
DOI: https://doi.org/10.1007/978-3-642-22822-3_33
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-22821-6
Online ISBN: 978-3-642-22822-3
eBook Packages: Computer ScienceComputer Science (R0)