Contextual anomaly detection in crowded surveillance scenes

Michael J.V. Leach, Ed.P. Sparks, Neil M. Robertson

Research output: Contribution to journalArticlepeer-review

34 Citations (Scopus)
250 Downloads (Pure)


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.
Original languageEnglish
Pages (from-to)71-79
Number of pages9
JournalPattern Recognition Letters
Early online date07 Dec 2013
Publication statusPublished - 15 Jul 2014

Bibliographical note

open access paper on journal website. authors final version uploaded


Dive into the research topics of 'Contextual anomaly detection in crowded surveillance scenes'. Together they form a unique fingerprint.

Cite this