DocumentCode :
3325213
Title :
Video anomaly detection in spatiotemporal context
Author :
Jiang, Fan ; Yuan, Junsong ; Tsaftaris, Sotirios A. ; Katsaggelos, Aggelos K.
Author_Institution :
Dept of EECS, Northwestern Univ., Evanston, IL, USA
fYear :
2010
fDate :
26-29 Sept. 2010
Firstpage :
705
Lastpage :
708
Abstract :
Compared to other approaches that analyze object trajectories, we propose to detect anomalous video events at three levels considering spatiotemporal context of video objects, i.e., point anomaly, sequential anomaly, and co-occurrence anomaly. A hierarchical data mining approach is proposed to achieve this task. At each level, the frequency based analysis is performed to automatically discover regular rules of normal events. The events deviating from these rules are detected as anomalies. Experiments on real traffic video prove that the detected video anomalies are hazardous or illegal according to the traffic rule.
Keywords :
data mining; spatiotemporal phenomena; traffic; video surveillance; anomalous video events; co-occurrence anomaly; frequency based analysis; hierarchical data mining approach; object trajectory; real traffic video anomaly detection; sequential anomaly; spatiotemporal context; video object; Context; Data mining; Hidden Markov models; Itemsets; Roads; Trajectory; Vehicles;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Image Processing (ICIP), 2010 17th IEEE International Conference on
Conference_Location :
Hong Kong
ISSN :
1522-4880
Print_ISBN :
978-1-4244-7992-4
Electronic_ISBN :
1522-4880
Type :
conf
DOI :
10.1109/ICIP.2010.5650993
Filename :
5650993
Link To Document :
بازگشت