File(s) under permanent embargo
Learning regularity in skeleton trajectories for anomaly detection in videos
conference contribution
posted on 2019-01-01, 00:00 authored by R Morais, Vuong Le, Truyen TranTruyen Tran, Budhaditya Saha, M Mansour, Svetha VenkateshSvetha Venkatesh© 2019 IEEE. Appearance features have been widely used in video anomaly detection even though they contain complex entangled factors. We propose a new method to model the normal patterns of human movements in surveillance video for anomaly detection using dynamic skeleton features. We decompose the skeletal movements into two sub-components: global body movement and local body posture. We model the dynamics and interaction of the coupled features in our novel Message-Passing Encoder-Decoder Recurrent Network. We observed that the decoupled features collaboratively interact in our spatio-temporal model to accurately identify human-related irregular events from surveillance video sequences. Compared to traditional appearance-based models, our method achieves superior outlier detection performance. Our model also offers 'open-box' examination and decision explanation made possible by the semantically understandable features and a network architecture supporting interpretability.
History
Event
Computer Vision and Pattern Recognition. Conference (2019 : Long Beach, California)Pagination
11988 - 11996Publisher
IEEELocation
Long Beach, CaliforniaPlace of publication
Piscataway, N.J.Publisher DOI
Start date
2019-06-15End date
2019-06-20ISSN
1063-6919ISBN-13
9781728132938Language
engPublication classification
E1 Full written paper - refereedTitle of proceedings
CVPR 2019 : Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern RecognitionUsage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC