Nonrigid Object Segmentation and Occlusion Detection in Image Sequences

DSpace Repository

Nonrigid Object Segmentation and Occlusion Detection in Image Sequences

Overview

Detailed record

dc.contributor.author Fundana, Ketut
dc.contributor.author Overgaard, Neils
dc.contributor.author Heyden, Anders
dc.contributor.author Gustafsson, David
dc.contributor.author Nielsen, Mads
dc.date.accessioned 2009-01-14T11:30:35Z
dc.date.available 2009-01-14T11:30:35Z
dc.date.issued 2008
dc.identifier.uri http://hdl.handle.net/2043/7393
dc.description.abstract We address the problem of nonrigid object segmentation in image sequences in the presence of occlusions. The proposed variational segmentation method is based on a region-based active contour of the Chan-Vese model augmented with a frame-to-frame interaction term as a shape prior. The interaction term is constructed to be pose-invariant by minimizing over a group of transformations and to allow moderate deformation in the shape of the contour. The segmentation method is then coupled with a novel variational contour matching formulation between two consecutive contours which gives a mapping of the intensities from the interior of the previous contour to the next. With this information occlusions can be detected and located using deviations from predicted intensities and the missing intensities in the occluded regions can be reconstructed. After reconstructing the occluded regions in the novel image, the segmentation can then be improved. Experimental results on synthetic and real image sequences are shown. en
dc.language.iso eng en
dc.subject image segmentation en
dc.subject variational methods en
dc.subject.classification Technology en
dc.title Nonrigid Object Segmentation and Occlusion Detection in Image Sequences en
dc.type Conference Paper, peer reviewed en
dc.identifier.paperprint 0 en
dc.contributor.department Malmö University. School of Technology en
dc.subject.srsc Research Subject Categories::TECHNOLOGY::Information technology::Computer science en
dc.subject.srsc Research Subject Categories::MATHEMATICS::Applied mathematics en
dc.relation.ispartofpublication Proceedings of International Conference on Computer Vision Theory and Applications
mahlocal.rights.oaType green
 Find Full text Files for download
Icon

This item appears in the following Collection(s)

Overview

Search


Browse

My Account

Statistics