Recurrent Bayesian Network for the recognition of Human Behaviors from Video

LES AUTEURS Nicolas Moenne-Loccoz, François Bremond, Monique Thonnat

RESUME:

We Propose an original bayesian approach to recognize human behaviors from video streams. Mobile objects and their visual features are computed by a vision module. Then, using a Recurrent Bayesian Network, behaviors of the mobile objects are recognized through the temporal evolution of their visual features.

Mots clé: Recurrent bayesian network, video interpretation, behavior recognition.

Pour télécharger cet article, cliquez ici

BibTeX reference:

Lecture Notes in Computer Science
Publisher: Springer-Verlag Heidelberg 
Volume: Volume 2626 / 2003. ICVS 2003, Graz, Austria, April 1-3, 2003. Proceedings

Dernière mise à jour : 22/07/03
Catherine.Martin@sophia.inria.fr