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

  • Authors:

  • Somboon Hongeng;Ram Nevatia;Francois Bremond

  • Affiliations:

  • Institute for Robotics and Intelligent Systems, University of Southern California, Los Angeles, CA and KOGS, FB Informatik, University of Hamburg, Vogt-Koelln-Str. 30, D-22527 Hamburg, Germany;Institute for Robotics and Intelligent Systems, University of Southern California, Los Angeles, CA;Institute for Robotics and Intelligent Systems, University of Southern California, Los Angeles, CA and INRIA Project ORION, 2004 Route des Lucioles BP 93, 06902 Sophia Antipolis Cedex, France

  • Venue:
  • Computer Vision and Image Understanding - Special issue on event detection in video
  • Year:
  • 2004

Quantified Score

Hi-index 0.00

Visualization

Abstract

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.