Multi-modal abnormality detection in video with unknown data segmentation Nguyen, Tien Vu, Phung, Dinh, Rana, Santu, Pham, Duc-Son and Venkatesh, Svetha 2012, Multi-modal abnormality detection in video with unknown data segmentation, in ICPR 2012 : Proceedings of 21st International Conference on Pattern Recognition, ICPR Organizing Committee, Tsubuka Science City, Japan, pp. 1322-1325. Attached Files Name Description MIMEType Size Downloads Title Multi-modal abnormality detection in video with unknown data segmentation Author(s) Nguyen, Tien Vu Phung, Dinh orcid.org/0000-0002-9977-8247 Rana, Santu orcid.org/0000-0003-2247-850X Pham, Duc-Son Venkatesh, Svetha orcid.org/0000-0001-8675-6631 Conference name International Conference on Pattern Recognition (21st : 2012 : Tsukuba Science City, Japan) Conference location Tsubuka Science City, Japan Conference dates 11-15 Nov. 2012 Title of proceedings ICPR 2012 : Proceedings of 21st International Conference on Pattern Recognition Editor(s) [Unknown] Publication date 2012 Conference series International Conference on Pattern Recognition Start page 1322 End page 1325 Total pages 4 Publisher ICPR Organizing Committee Place of publication Tsubuka Science City, Japan Keyword(s) hidden Markov models image segmentation video cameras Summary 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 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. ISBN 9784990644109 Language eng Field of Research 080104 Computer Vision 080109 Pattern Recognition and Data Mining Socio Economic Objective 899999 Information and Communication Services not elsewhere classified HERDC Research category E1 Full written paper - refereed Persistent URL http://hdl.handle.net/10536/DRO/DU:30052645 Document type: Conference Paper Collections: Faculty of Science, Engineering and Built Environment Centre for Pattern Recognition and Data Analytics (PRADA) 2018 ERA Submission Related Links Link Description Connect to published version (restricted access) Go to link with your DU access privileges     Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved. Versions Version Filter Type Fri, 24 May 2013, 12:10:43 EST Fri, 24 May 2013, 14:25:01 EST Fri, 24 May 2013, 14:57:19 EST Fri, 24 May 2013, 14:58:38 EST Mon, 27 May 2013, 08:41:52 EST Mon, 27 May 2013, 14:01:18 EST Mon, 10 Jun 2013, 10:31:57 EST Wed, 21 Oct 2015, 14:47:09 EST Wed, 21 Oct 2015, 18:08:36 EST Mon, 06 Jun 2016, 12:36:27 EST Thu, 01 Jun 2017, 15:45:12 EST Filtered Full Citation counts:   Cited 0 times in TR Web of Science Cited 3 times in Scopus Search Google Scholar Access Statistics: 588 Abstract Views, 8 File Downloads  -  Detailed Statistics Created: Fri, 24 May 2013, 12:10:43 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.