Effective crowd anomaly detection through spatio-temporal texture analysis

HAO, Yu, XU, Zhi-Jie, LIU, Ying, WANG, Jing and FAN, Jiu-Lun (2018). Effective crowd anomaly detection through spatio-temporal texture analysis. International Journal of Automation and Computing.

[img]
Preview
PDF
Hao2018_Article_EffectiveCrowdAnomalyDetection.pdf - Published Version
Creative Commons Attribution.

Download (2MB) | Preview
Official URL: https://link.springer.com/article/10.1007%2Fs11633...
Open Access URL: https://link.springer.com/content/pdf/10.1007%2Fs1...
Link to published version:: https://doi.org/10.1007/s11633-018-1141-z

Abstract

Abnormal crowd behaviors in high density situations can pose great danger to public safety. Despite the extensive installation of closed-circuit television (CCTV) cameras, it is still difficult to achieve real-time alerts and automated responses from current systems. Two major breakthroughs have been reported in this research. Firstly, a spatial-temporal texture extraction algorithm is developed. This algorithm is able to effectively extract video textures with abundant crowd motion details. It is through adopting Gabor-filtered textures with the highest information entropy values. Secondly, a novel scheme for defining crowd motion patterns (signatures) is devised to identify abnormal behaviors in the crowd by employing an enhanced gray level co-occurrence matrix model. In the experiments, various classic classifiers are utilized to benchmark the performance of the proposed method. The results obtained exhibit detection and accuracy rates which are, overall, superior to other techniques.

Item Type: Article
Research Institute, Centre or Group: Cultural Communication and Computing Research Institute > Communication and Computing Research Centre
Identification Number: https://doi.org/10.1007/s11633-018-1141-z
Depositing User: Carmel House
Date Deposited: 15 Oct 2018 10:58
Last Modified: 16 Nov 2018 12:20
URI: http://shura.shu.ac.uk/id/eprint/22925

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics