Contextual anomaly detection in crowded surveillance scenes


Autoria(s): Leach, Michael J.V.; Sparks, Ed.P.; Robertson, Neil M.
Data(s)

15/07/2014

Resumo

This work addresses the problem of detecting human behavioural anomalies in crowded surveillance environments. We focus in particular on the problem of detecting subtle anomalies in a behaviourally heterogeneous surveillance scene. To reach this goal we implement a novel unsupervised context-aware process. We propose and evaluate a method of utilising social context and scene context to improve behaviour analysis. We find that in a crowded scene the application of Mutual Information based social context permits the ability to prevent self-justifying groups and propagate anomalies in a social network, granting a greater anomaly detection capability. Scene context uniformly improves the detection of anomalies in both datasets. The strength of our contextual features is demonstrated by the detection of subtly abnormal behaviours, which otherwise remain indistinguishable from normal behaviour.

Formato

application/pdf

Identificador

http://pure.qub.ac.uk/portal/en/publications/contextual-anomaly-detection-in-crowded-surveillance-scenes(cd4692a9-d6ae-413d-ae23-d37dddc48b16).html

http://dx.doi.org/10.1016/j.patrec.2013.11.018

http://pure.qub.ac.uk/ws/files/57462725/Anomaly1_s2.0_S0167865513004625_main.pdf

Idioma(s)

eng

Direitos

info:eu-repo/semantics/openAccess

Fonte

Leach , M J V , Sparks , E P & Robertson , N M 2014 , ' Contextual anomaly detection in crowded surveillance scenes ' Pattern Recognition Letters , pp. 71-79 . DOI: 10.1016/j.patrec.2013.11.018

Tipo

article