Combining image regions and human activity for indirect object recognition in indoor wide-angle views Peursum, Patrick, West, Geoff and Venkatesh, Svetha 2005, Combining image regions and human activity for indirect object recognition in indoor wide-angle views, in ICCV 2005 : Proceedings of the IEEE International Conference on Computer Vision, IEEE, Los Alamitos, Calif., pp. 82-89, doi: 10.1109/ICCV.2005.57. Attached Files Name Description MIMEType Size Downloads venkatesh-combiningimage-2005.pdf Published version application/pdf 569.87KB 111 Title Combining image regions and human activity for indirect object recognition in indoor wide-angle views Author(s) Peursum, Patrick West, Geoff Venkatesh, Svetha orcid.org/0000-0001-8675-6631 Conference name IEEE International Conference on Computer Vision (10th : 2005 : Beijing, China) Conference location Beijing, China Conference dates 17-20 Oct. 2005 Title of proceedings ICCV 2005 : Proceedings of the IEEE International Conference on Computer Vision Editor(s) [Unknown] Publication date 2005 Conference series International Conference on Computer Vision Start page 82 End page 89 Total pages 8 Publisher IEEE Place of publication Los Alamitos, Calif. Keyword(s) Bayesian methods computer vision humans layout object recognition shape smart homes surveillance Summary Traditional methods of object recognition are reliant on shape and so are very difficult to apply in cluttered, wideangle and low-detail views such as surveillance scenes. To address this, a method of indirect object recognition is proposed, where human activity is used to infer both the location and identity of objects. No shape analysis is necessary. The concept is dubbed 'interaction signatures', since the premise is that a human will interact with objects in ways characteristic of the function of that object - for example, a person sits in a chair and drinks from a cup. The human-centred approach means that recognition is possible in low-detail views and is largely invariant to the shape of objects within the same functional class. This paper implements a Bayesian network for classifying region patches with object labels, building upon our previous work in automatically segmenting and recognising a human's interactions with the objects. Experiments show that interaction signatures can successfully find and label objects in low-detail views and are equally effective at recognising test objects that differ markedly in appearance from the training objects. Notes This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder. ISBN 9780769523347 076952334X ISSN 1550-5499 Language eng DOI 10.1109/ICCV.2005.57 Field of Research 089999 Information and Computing Sciences not elsewhere classified Socio Economic Objective 970108 Expanding Knowledge in the Information and Computing Sciences HERDC Research category E1.1 Full written paper - refereed Copyright notice ©2005, IEEE Persistent URL http://hdl.handle.net/10536/DRO/DU:30044614 Document type: Conference Paper Collections: School of Information Technology Open Access Collection 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. 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. Versions Version Filter Type Fri, 20 Apr 2012, 11:35:28 EST Fri, 27 Apr 2012, 12:38:25 EST Fri, 27 Apr 2012, 12:39:09 EST Fri, 27 Apr 2012, 12:40:15 EST Thu, 03 May 2012, 11:56:40 EST Filtered Full Citation counts:   Cited 0 times in TR Web of Science Cited 33 times in Scopus Search Google Scholar Access Statistics: 240 Abstract Views, 111 File Downloads  -  Detailed Statistics Created: Fri, 20 Apr 2012, 11:35:28 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.