File(s) under permanent embargo
Multi-modal abnormality detection in video with unknown data segmentation
conference contribution
posted on 2012-01-01, 00:00 authored by Tien Vu Nguyen, Quoc-Dinh Phung, Santu RanaSantu Rana, D S Pham, Svetha VenkateshSvetha VenkateshThis paper examines a new problem in large scale stream data: abnormality detection which is localized to a data segmentation process. Unlike traditional abnormality detection methods which typically build one unified model across data stream, we propose that building multiple detection models focused on different coherent sections of the video stream would result in better detection performance. One key challenge is to segment the data into coherent sections as the number of segments is not known in advance and can vary greatly across cameras; and a principled way approach is required. To this end, we first employ the recently proposed infinite HMM and collapsed Gibbs inference to automatically infer data segmentation followed by constructing abnormality detection models which are localized to each segmentation. We demonstrate the superior performance of the proposed framework in a real-world surveillance camera data over 14 days.
History
Event
International Conference on Pattern Recognition (21st : 2012 : Tsukuba Science City, Japan)Pagination
1322 - 1325Publisher
ICPR Organizing CommitteeLocation
Tsubuka Science City, JapanPlace of publication
Tsubuka Science City, JapanStart date
2012-11-11End date
2012-11-15ISBN-13
9784990644109Language
engPublication classification
E1 Full written paper - refereedTitle of proceedings
ICPR 2012 : Proceedings of 21st International Conference on Pattern RecognitionUsage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC