Localized Anomaly Detection via Hierarchical Integrated Activity Discovery

Abstract : With the increasing number and variety of camera instal- lations, unsupervised methods that learn typical activities have become popular for anomaly detection. In this article, we consider recent methods based on temporal probabilistic models and improve them in multiple ways. Our contributions are the following: (i) we integrate the low level processing and the temporal activity modeling, showing how this feedback improves the overall quality of the captured information, (ii) we show how the same approach can be taken to do hierarchical multi-camera processing, (iii) we use spatial analysis of the anomalies both to perform local anomaly detection and to frame automatically the detected anomalies. We illustrate the approach on both traffic data and videos coming from a metro station.
Type de document :
Communication dans un congrès
AVSS - IEEE International Conference on Advanced Video and Signal-Based Surveillance, Aug 2013, Kraków, Poland. 2013
Liste complète des métadonnées

https://hal.inria.fr/hal-00872057
Contributeur : Rémi Emonet <>
Soumis le : vendredi 11 octobre 2013 - 11:06:20
Dernière modification le : lundi 12 février 2018 - 10:16:06

Identifiants

  • HAL Id : hal-00872057, version 1

Citation

Thiyagarajan Chockalingam, Rémi Emonet, Jean-Marc Odobez. Localized Anomaly Detection via Hierarchical Integrated Activity Discovery. AVSS - IEEE International Conference on Advanced Video and Signal-Based Surveillance, Aug 2013, Kraków, Poland. 2013. 〈hal-00872057〉

Partager

Métriques

Consultations de la notice

28