A Bayesian Computer Vision System for Modeling Human Interaction
ICVS '99 Proceedings of the First International Conference on Computer Vision Systems
Lucas/Kanade meets Horn/Schunck: combining local and global optic flow methods
International Journal of Computer Vision
Energy-Based Models in Document Recognition and Computer Vision
ICDAR '07 Proceedings of the Ninth International Conference on Document Analysis and Recognition - Volume 01
Activity recognition by integrating the physics of motion with a neuromorphic model of perception
WMVC'09 Proceedings of the 2009 international conference on Motion and video computing
Query-based retrieval of complex activities using "strings of motion-words"
WMVC'09 Proceedings of the 2009 international conference on Motion and video computing
Machine Recognition of Human Activities: A Survey
IEEE Transactions on Circuits and Systems for Video Technology
| Hi-index | 0.00 |
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.