A generic framework for video understanding applied to group behavior recognition

Sofia Zaidenberg 1 Bernard Boulay 1 François Bremond 1
1 STARS - Spatio-Temporal Activity Recognition Systems
CRISAM - Inria Sophia Antipolis - Méditerranée
Abstract : This paper presents an approach to detect and track groups of people in video-surveillance applications, and to automatically recognize their behavior. This method keeps track of individuals moving together by maintaining a spacial and temporal group coherence. First, people are individually detected and tracked. Second, their trajectories are analyzed over a temporal window and clustered using the Mean-Shift algorithm. A coherence value describes how well a set of people can be described as a group. Furthermore, we propose a formal event description language. The group events recognition approach is successfully validated on 4 camera views from 3 datasets: an airport, a subway, a shopping center corridor and an entrance hall.
Type de document :
Communication dans un congrès
9th IEEE International Conference on Advanced Video and Signal-Based Surveillance (AVSS 2012), Sep 2012, Beijing, China. IEEE Computer Society, pp.136 -142, 2012, Advanced Video and Signal Based Surveillance, IEEE Conference on. 〈10.1109/AVSS.2012.1〉
Liste complète des métadonnées

Littérature citée [17 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-00702179
Contributeur : Sofia Zaidenberg <>
Soumis le : mercredi 20 juin 2012 - 14:41:30
Dernière modification le : jeudi 11 janvier 2018 - 16:20:38
Document(s) archivé(s) le : jeudi 15 décembre 2016 - 09:31:48

Fichiers

avss.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Sofia Zaidenberg, Bernard Boulay, François Bremond. A generic framework for video understanding applied to group behavior recognition. 9th IEEE International Conference on Advanced Video and Signal-Based Surveillance (AVSS 2012), Sep 2012, Beijing, China. IEEE Computer Society, pp.136 -142, 2012, Advanced Video and Signal Based Surveillance, IEEE Conference on. 〈10.1109/AVSS.2012.1〉. 〈hal-00702179〉

Partager

Métriques

Consultations de la notice

308

Téléchargements de fichiers

290