Spatio-temporal texture modelling for real-time crowd anomaly detection

Jing Wang, Zhijie Xu

Research output: Contribution to journal › Article

25 Citations (Scopus)

Abstract

With the rapidly increasing demands from surveillance and security industries, crowd behaviour analysis has become one of the hotly pursued video event detection frontiers within the computer vision arena in recent years. This research has investigated innovative crowd behaviour detection approaches based on statistical crowd features extracted from video footages. In this paper, a new crowd video anomaly detection algorithm has been developed based on analysing the extracted spatio-temporal textures. The algorithm has been designed for real-time applications by deploying low-level statistical features and alleviating complicated machine learning and recognition processes. In the experiments, the system has been proven a valid solution for detecting anomaly behaviours without strong assumptions on the nature of crowds, for example, subjects and density. The developed prototype shows improved adaptability and efficiency against chosen benchmark systems.
LanguageEnglish
Pages177-187
Number of pages11
JournalComputer Vision and Image Understanding
Volume144
DOIs
Publication statusPublished - Mar 2016

Fingerprint

Textures
Computer vision
Learning systems
Industry
Experiments

Cite this

Wang, Jing ; Xu, Zhijie. / Spatio-temporal texture modelling for real-time crowd anomaly detection. In: Computer Vision and Image Understanding. 2016 ; Vol. 144. pp. 177-187.
@article{0540ffb015034b49859fe46ebf848772,
title = "Spatio-temporal texture modelling for real-time crowd anomaly detection",
abstract = "With the rapidly increasing demands from surveillance and security industries, crowd behaviour analysis has become one of the hotly pursued video event detection frontiers within the computer vision arena in recent years. This research has investigated innovative crowd behaviour detection approaches based on statistical crowd features extracted from video footages. In this paper, a new crowd video anomaly detection algorithm has been developed based on analysing the extracted spatio-temporal textures. The algorithm has been designed for real-time applications by deploying low-level statistical features and alleviating complicated machine learning and recognition processes. In the experiments, the system has been proven a valid solution for detecting anomaly behaviours without strong assumptions on the nature of crowds, for example, subjects and density. The developed prototype shows improved adaptability and efficiency against chosen benchmark systems.",
keywords = "Crowd anomaly, Spatio-temporal texture, Spatio-temporal volume",
author = "Jing Wang and Zhijie Xu",
year = "2016",
month = "3",
doi = "10.1016/j.cviu.2015.08.010",
language = "English",
volume = "144",
pages = "177--187",
journal = "Computer Vision and Image Understanding",
issn = "1077-3142",
publisher = "Academic Press Inc.",

}

Wang, J & Xu, Z 2016, 'Spatio-temporal texture modelling for real-time crowd anomaly detection', Computer Vision and Image Understanding, vol. 144, pp. 177-187. https://doi.org/10.1016/j.cviu.2015.08.010

Spatio-temporal texture modelling for real-time crowd anomaly detection. / Wang, Jing; Xu, Zhijie.

In: Computer Vision and Image Understanding, Vol. 144, 03.2016, p. 177-187.

Research output: Contribution to journal › Article

TY - JOUR

T1 - Spatio-temporal texture modelling for real-time crowd anomaly detection

AU - Wang, Jing

AU - Xu, Zhijie

PY - 2016/3

Y1 - 2016/3

N2 - With the rapidly increasing demands from surveillance and security industries, crowd behaviour analysis has become one of the hotly pursued video event detection frontiers within the computer vision arena in recent years. This research has investigated innovative crowd behaviour detection approaches based on statistical crowd features extracted from video footages. In this paper, a new crowd video anomaly detection algorithm has been developed based on analysing the extracted spatio-temporal textures. The algorithm has been designed for real-time applications by deploying low-level statistical features and alleviating complicated machine learning and recognition processes. In the experiments, the system has been proven a valid solution for detecting anomaly behaviours without strong assumptions on the nature of crowds, for example, subjects and density. The developed prototype shows improved adaptability and efficiency against chosen benchmark systems.

AB - With the rapidly increasing demands from surveillance and security industries, crowd behaviour analysis has become one of the hotly pursued video event detection frontiers within the computer vision arena in recent years. This research has investigated innovative crowd behaviour detection approaches based on statistical crowd features extracted from video footages. In this paper, a new crowd video anomaly detection algorithm has been developed based on analysing the extracted spatio-temporal textures. The algorithm has been designed for real-time applications by deploying low-level statistical features and alleviating complicated machine learning and recognition processes. In the experiments, the system has been proven a valid solution for detecting anomaly behaviours without strong assumptions on the nature of crowds, for example, subjects and density. The developed prototype shows improved adaptability and efficiency against chosen benchmark systems.

KW - Crowd anomaly

KW - Spatio-temporal texture

KW - Spatio-temporal volume

UR - http://www.scopus.com/inward/record.url?scp=84956610770&partnerID=8YFLogxK

U2 - 10.1016/j.cviu.2015.08.010

DO - 10.1016/j.cviu.2015.08.010

M3 - Article

VL - 144

SP - 177

EP - 187

JO - Computer Vision and Image Understanding

T2 - Computer Vision and Image Understanding

JF - Computer Vision and Image Understanding

SN - 1077-3142

ER -

Wang J, Xu Z. Spatio-temporal texture modelling for real-time crowd anomaly detection. Computer Vision and Image Understanding. 2016 Mar;144:177-187. https://doi.org/10.1016/j.cviu.2015.08.010

Access to Document