Show simple item record

dc.contributor.authorPehlivan, S.en_US
dc.contributor.authorDuygulu, P.en_US
dc.date.accessioned2016-02-08T09:54:35Z
dc.date.available2016-02-08T09:54:35Z
dc.date.issued2011-02en_US
dc.identifier.issn1077-3142
dc.identifier.urihttp://hdl.handle.net/11693/22038
dc.description.abstractWe address the problem of recognizing actions from arbitrary views for a multi-camera system. We argue that poses are important for understanding human actions and the strength of the pose representation affects the overall performance of the action recognition system. Based on this idea, we present a new view-independent representation for human poses. Assuming that the data is initially provided in the form of volumetric data, the volume of the human body is first divided into a sequence of horizontal layers, and then the intersections of the body segments with each layer are coded with enclosing circles. The circular features in all layers (i) the number of circles, (ii) the area of the outer circle, and (iii) the area of the inner circle are then used to generate a pose descriptor. The pose descriptors of all frames in an action sequence are further combined to generate corresponding motion descriptors. Action recognition is then performed with a simple nearest neighbor classifier. Experiments performed on the benchmark IXMAS multi-view dataset demonstrate that the performance of our method is comparable to the other methods in the literature. © 2010 Elsevier Inc. All rights reserved.en_US
dc.language.isoEnglishen_US
dc.source.titleComputer Vision and Image Understandingen_US
dc.relation.isversionofhttp://dx.doi.org/10.1016/j.cviu.20http://dx.doi.org/10.11.004en_US
dc.subjectAction recognitionen_US
dc.subjectArbitrary viewen_US
dc.subjectMulti - cameraen_US
dc.subjectPose representationen_US
dc.titleA new pose-based representation for recognizing actions from multiple camerasen_US
dc.typeArticleen_US
dc.departmentDepartment of Computer Engineeringen_US
dc.citation.spage140en_US
dc.citation.epage151en_US
dc.citation.volumeNumber115en_US
dc.citation.issueNumber2en_US
dc.identifier.doi10.1016/j.cviu.2010.11.004en_US
dc.publisherAcademic Pressen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record