eprintid: 801
rev_number: 18
eprint_status: archive
userid: 35
dir: disk0/00/00/08/01
datestamp: 2011-08-11 12:06:29
lastmod: 2013-03-05 15:14:19
status_changed: 2011-08-11 12:06:29
type: article
metadata_visibility: show
item_issues_count: 0
creators_name: Jiang, Fan
creators_name: Yuanc, Junsong 
creators_name: Tsaftaris, Sotirios A.
creators_name: Katsaggelos, Aggelos K.
creators_id: 
creators_id: 
creators_id: sotirios.tsaftaris@imtlucca.it
creators_id: 
title: Anomalous video event detection using spatiotemporal context
ispublished: pub
subjects: TK
divisions: CSA
full_text_status: none
keywords: Video surveillance; Anomaly detection; Data mining; Clustering; Context
note: Special issue on Feature-Oriented Image and Video Computing for Extracting Contexts and Semantics
abstract: Compared to other anomalous video event detection approaches that analyze object trajectories only, we propose a context-aware method to detect anomalies. By tracking all moving objects in the video, three different levels of spatiotemporal contexts are considered, i.e., point anomaly of a video object, sequential anomaly of an object trajectory, and co-occurrence anomaly of multiple video objects. A hierarchical data mining approach is proposed. At each level, frequency-based analysis is performed to automatically discover regular rules of normal events. Events deviating from these rules are identified as anomalies. The proposed method is computationally efficient and can infer complex rules. Experiments on real traffic video validate that the detected video anomalies are hazardous or illegal according to traffic regulations.
date: 2011-03
date_type: published
publication: Computer vision and image understanding
volume: 115
number: 3
publisher: Elsevier
pagerange: 323 - 333
id_number: 10.1016/j.cviu.2010.10.008
refereed: TRUE
issn: 1077-3142
official_url: http://www.sciencedirect.com/science/article/pii/S1077314210002390
citation:   Jiang, Fan and Yuanc, Junsong  and Tsaftaris, Sotirios A. and Katsaggelos, Aggelos K.  Anomalous video event detection using spatiotemporal context.  Computer vision and image understanding, 115 (3).  323 - 333.  ISSN 1077-3142      (2011)