Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Detecting violent and abnormal crowd activity using temporal analysis of grey level co-occurrence matrix (GLCM)-based texture measures

Lloyd, Kaelon, Rosin, Paul L., Marshall, Andrew David and Moore, Simon Christopher 2017. Detecting violent and abnormal crowd activity using temporal analysis of grey level co-occurrence matrix (GLCM)-based texture measures. Machine Vision and Applications 28 (3) , pp. 361-371. 10.1007/s00138-017-0830-x

PDF - Published Version
Available under License Creative Commons Attribution.

Download (1MB) | Preview


The severity of sustained injury resulting from assault-related violence can be minimized by reducing detection time. However, it has been shown that human operators perform poorly at detecting events found in video footage when presented with simultaneous feeds. We utilize computer vision techniques to develop an automated method of violence detection that can aid a human operator. We observed that violence in city centre environments often occur in crowded areas, resulting in individual actions being occluded by other crowd members. Measures of visual texture have shown to be effective at encoding crowd appearance. Therefore, we propose modelling crowd dynamics using changes in crowd texture. We refer to this approach as Violent Crowd Texture (VCT). Real-world surveillance footage of night time environments and the violent flows dataset were tested using a random forest classifier to evaluate the ability of the VCT method at discriminating between violent and non-violent behaviour. Our method achieves ROC values of 0.98 and 0.91 on our own real world CCTV dataset and the violent flows dataset respectively.

Item Type: Article
Date Type: Publication
Status: Published
Schools: Computer Science & Informatics
Crime and Security Research Institute (CSURI)
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
R Medicine > RK Dentistry
Uncontrolled Keywords: Violence, Crowd, CCTV, Texture, GLCM
Publisher: Springer Verlag
ISSN: 0932-8092
Funders: Engineering and Physical Sciences Research Council
Date of First Compliant Deposit: 1 June 2016
Date of Acceptance: 1 June 2016
Last Modified: 29 Jul 2019 16:29

Citation Data

Cited 30 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item Edit Item


Downloads per month over past year

View more statistics