Show simple item record

dc.contributor.authorNguyen, T.
dc.contributor.authorRana, S.
dc.contributor.authorPhung, D.
dc.contributor.authorPham, DucSon
dc.contributor.authorVenkatesh, S.
dc.contributor.editorN/A
dc.date.accessioned2017-01-30T15:00:08Z
dc.date.available2017-01-30T15:00:08Z
dc.date.created2013-02-18T20:00:44Z
dc.date.issued2012
dc.identifier.citationNguyen, Tien Vu and Phung, Dinh and Rana, Santu and Pham, Duc Son and Venkatesh, Svetha. 2012. Multi-modal abnormality detection in video with unknown data segmentation, in Proceedings of the 21st International Conference on Pattern Recognition (ICPR 2012), Nov 11-15 2012, pp. 1322-1325. Tsukuba, Japan: IEEE.
dc.identifier.urihttp://hdl.handle.net/20.500.11937/42528
dc.description.abstract

This 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 pro-posed 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.

dc.publisherIEEE
dc.relation.urihttp://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6460383
dc.subjectvectors
dc.subjectdetectors
dc.subjectsurveillance
dc.subjecthidden Markov models
dc.subjectcomputational modeling
dc.subjectdata models
dc.subjectcameras
dc.titleMulti-modal abnormality detection in video with unknown data segmentation
dc.typeConference Paper
dcterms.source.titleProceedings of the International Conference on Pattern Recognition
dcterms.source.seriesProceedings of the International Conference on Pattern Recognition
dcterms.source.isbn9784990644116
dcterms.source.conferenceThe International Conference on Pattern Recognition
dcterms.source.conference-start-dateNov 11 2012
dcterms.source.conferencelocationTsukuba Science City, Japan
dcterms.source.placeUSA
curtin.department
curtin.accessStatusFulltext not available


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record