Crowd anomaly detection for automated video surveillance

Jing Wang, Zhijie Xu

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Citations (Scopus)


Video-based crowd behaviour detection aims at tackling challenging problems such as automating and identifying changing crowd behaviours under complex real life situations. In this paper, real-time crowd anomaly detection algorithms have been investigated. Based on the spatio-temporal video volume concept, an innovative spatio-temporal texture model has been proposed in this research for its rich crowd pattern characteristics. Through extracting and integrating those crowd textures from surveillance recordings, a redundancy wavelet transformation-based feature space can be deployed for behavioural template matching. Experiment shows that the abnormality appearing in crowd scenes can be identified in a real-time fashion by the devised method. This new approach is envisaged to facilitate a wide spectrum of crowd analysis applications through automating current Closed-Circuit Television (CCTV)-based surveillance systems.

Original languageEnglish
Title of host publicationIET Seminar Digest
PublisherInstitution of Engineering and Technology
Publication statusPublished - 2015
Event6th International Conference on Imaging for Crime Prevention and Detection - London, United Kingdom
Duration: 15 Jul 201517 Jul 2015
Conference number: 6 (Link to Conference Details)


Conference6th International Conference on Imaging for Crime Prevention and Detection
Abbreviated titleICDP 2015
CountryUnited Kingdom
Internet address


Dive into the research topics of 'Crowd anomaly detection for automated video surveillance'. Together they form a unique fingerprint.

Cite this