Crowd Event Recognition using HOG Tracker

Carolina Garate 1 Piotr Bilinski 1 François Bremond 1
1 PULSAR - Perception Understanding Learning Systems for Activity Recognition
CRISAM - Inria Sophia Antipolis - Méditerranée
Abstract : The recognition in real time of crowd dynamics in public places are becoming essential to avoid crowd related disasters and ensure safety of people. We present in this paper a new approach for Crowd Event Recognition. Our study begins with a novel tracking method, based on HOG descriptors, to finally use pre-defined models (i.e. crowd scenarios) to recognize crowd events. We define these scenarios using statistics analysis from the data sets used in the experimentation. The approach is characterized by combining a local analysis with a global analysis for crowd behavior recognition. The local analysis is enabled by a robust tracking method, and global analysis is done by a scenario modeling stage.
Type de document :
Communication dans un congrès
Twelfth IEEE International Workshop on Performance Evaluation of Tracking and Surveillance (PETS-Winter), Dec 2009, Snowbird, UT, United States. IEEE, pp.1-6, 2009, 〈10.1109/PETS-WINTER.2009.5399727〉
Liste complète des métadonnées

Littérature citée [18 références]  Voir  Masquer  Télécharger
https://hal.inria.fr/inria-00515197
Contributeur : Piotr Bilinski <>
Soumis le : vendredi 14 décembre 2012 - 19:58:09
Dernière modification le : mardi 24 juillet 2018 - 15:48:06
Document(s) archivé(s) le : vendredi 15 mars 2013 - 03:52:59

Fichier

PETS-Winter09.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

INRIA

Citation

Carolina Garate, Piotr Bilinski, François Bremond. Crowd Event Recognition using HOG Tracker. Twelfth IEEE International Workshop on Performance Evaluation of Tracking and Surveillance (PETS-Winter), Dec 2009, Snowbird, UT, United States. IEEE, pp.1-6, 2009, 〈10.1109/PETS-WINTER.2009.5399727〉. 〈inria-00515197v2〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

318

Téléchargements de fichiers

393

Contact


archive-ouverte@inria.fr