From Local Temporal Correlation to Global Anomaly Detection

Abstract : In this paper, we propose a novel framework tailored towards global video behaviour anomaly detection in complex outdoor scenes involving multiple temporal processes caused by correlated behaviours of multiple objects. Specifically, given a complex wide-area scene that has been segmented automatically into semantic regions where behaviour patterns are represented as discrete local atomic events, we formulate a novel cascade of Hidden Markov Models to model behaviours with complex temporal correlations by utilising combinatory evidences collected from local atomic events. Using a cascade configuration not only allows for accurate detection of video behaviour anomalies, more importantly, it also improves the robustness of the model in dealing with the inevitable presence of errors and noise in the behaviour representation resulting less false alarms. We evaluate the effectiveness of the proposed framework on a real world traffic scene. The results demonstrate that the framework is able to detect not only anomalies that are visually obvious, but also those that are ambiguous or supported only by very weak visual evidence, e.g. those that can be easily missed by a human observer.
Type de document :
Communication dans un congrès
The 1st International Workshop on Machine Learning for Vision-based Motion Analysis - MLVMA'08, Oct 2008, Marseille, France. 2008
Liste complète des métadonnées

Littérature citée [14 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00326724
Contributeur : Peter Sturm <>
Soumis le : dimanche 5 octobre 2008 - 12:48:30
Dernière modification le : lundi 6 octobre 2008 - 09:39:29
Document(s) archivé(s) le : jeudi 3 juin 2010 - 21:30:00

Fichier

mlvma08_submission_12.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00326724, version 1

Collections

Citation

Chen Change Loy, Tao Xiang, Shaogang Gong. From Local Temporal Correlation to Global Anomaly Detection. The 1st International Workshop on Machine Learning for Vision-based Motion Analysis - MLVMA'08, Oct 2008, Marseille, France. 2008. 〈inria-00326724〉

Partager

Métriques

Consultations de la notice

271

Téléchargements de fichiers

132