Sciweavers

CVIU
2004

Video-based event recognition: activity representation and probabilistic recognition methods

13 years 3 months ago
Video-based event recognition: activity representation and probabilistic recognition methods
We present a new representation and recognition method for human activities. An activity is considered to be composed of action threads, each thread being executed by a single actor. A single-thread action is represented by a stochastic finite automaton of event states, which are recognized from the characteristics of the trajectory and shape of moving blob of the actor using Bayesian methods. A multi-agent event is composed of several action threads related by temporal constraints. Multi-agent events are recognized by propagating the constraints and likelihood of event threads in a temporal logic network. We present results on real-world data and performance characterization on perturbed data.
Somboon Hongeng, Ramakant Nevatia, François
Added 17 Dec 2010
Updated 17 Dec 2010
Type Journal
Year 2004
Where CVIU
Authors Somboon Hongeng, Ramakant Nevatia, François Brémond
Comments (0)