Crowd anomaly detection for automated video surveillance

Jing Wang, Zhijie Xu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

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
Volume2015
Edition5
DOIs
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
https://communities.theiet.org/communities/events/item/122/39/7868 (Link to Conference Details)

Conference

Conference6th International Conference on Imaging for Crime Prevention and Detection
Abbreviated titleICDP 2015
CountryUnited Kingdom
CityLondon
Period15/07/1517/07/15
Internet address

Fingerprint

Textures
Template matching
Television
Redundancy
Networks (circuits)
Experiments

Cite this

Wang, J., & Xu, Z. (2015). Crowd anomaly detection for automated video surveillance. In IET Seminar Digest (5 ed., Vol. 2015). Institution of Engineering and Technology. https://doi.org/10.1049/ic.2015.0102
Wang, Jing ; Xu, Zhijie. / Crowd anomaly detection for automated video surveillance. IET Seminar Digest. Vol. 2015 5. ed. Institution of Engineering and Technology, 2015.
@inproceedings{508390d2df9b4ccaa55b15d2b318d309,
title = "Crowd anomaly detection for automated video surveillance",
abstract = "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.",
keywords = "Crowd behaviour, Optical flow, Spatiotemporal texture, Video surveillance, Wavelet transformation",
author = "Jing Wang and Zhijie Xu",
year = "2015",
doi = "10.1049/ic.2015.0102",
language = "English",
volume = "2015",
booktitle = "IET Seminar Digest",
publisher = "Institution of Engineering and Technology",
address = "United Kingdom",
edition = "5",

}

Wang, J & Xu, Z 2015, Crowd anomaly detection for automated video surveillance. in IET Seminar Digest. 5 edn, vol. 2015, Institution of Engineering and Technology, 6th International Conference on Imaging for Crime Prevention and Detection, London, United Kingdom, 15/07/15. https://doi.org/10.1049/ic.2015.0102

Crowd anomaly detection for automated video surveillance. / Wang, Jing; Xu, Zhijie.

IET Seminar Digest. Vol. 2015 5. ed. Institution of Engineering and Technology, 2015.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Crowd anomaly detection for automated video surveillance

AU - Wang, Jing

AU - Xu, Zhijie

PY - 2015

Y1 - 2015

N2 - 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.

AB - 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.

KW - Crowd behaviour

KW - Optical flow

KW - Spatiotemporal texture

KW - Video surveillance

KW - Wavelet transformation

UR - http://www.scopus.com/inward/record.url?scp=84946063245&partnerID=8YFLogxK

U2 - 10.1049/ic.2015.0102

DO - 10.1049/ic.2015.0102

M3 - Conference contribution

VL - 2015

BT - IET Seminar Digest

PB - Institution of Engineering and Technology

ER -

Wang J, Xu Z. Crowd anomaly detection for automated video surveillance. In IET Seminar Digest. 5 ed. Vol. 2015. Institution of Engineering and Technology. 2015 https://doi.org/10.1049/ic.2015.0102