Show simple item record

dc.contributor.authorTuncel, E.en_US
dc.contributor.authorOnural, L.en_US
dc.date.accessioned2016-02-08T10:37:39Z
dc.date.available2016-02-08T10:37:39Z
dc.date.issued2000en_US
dc.identifier.issn1051-8215
dc.identifier.urihttp://hdl.handle.net/11693/25012
dc.description.abstractA novel video-object segmentation algorithm is proposed, which takes the previously estimated 2-D dense motion vector field as input and uses the generalized recursive shortest spanning tree method to approximate each component of the motion vector field as a piecewise planar function. The algorithm is successful in capturing 3-D planar objects in the scene correctly, with acceptable accuracy at the boundaries. The proposed algorithm is fast and requires no initial guess about the segmentation mask. Moreover, it is a hierarchical scheme which gives finest to coarsest segmentation results. The only external parameter needed by the algorithm is the number of segmented regions that essentially control the level at which the coarseness the algorithm would stop. The proposed algorithm improves the `analysis model' developed in the European COST211 framework.en_US
dc.language.isoEnglishen_US
dc.source.titleIEEE Transactions on Circuits and Systems for Video Technologyen_US
dc.relation.isversionofhttp://dx.doi.org/10.1109/76.856454en_US
dc.subjectAlgorithmsen_US
dc.subjectMultimedia systemsen_US
dc.subjectObject recognitionen_US
dc.subjectPiecewise linear techniquesen_US
dc.subjectTrees (mathematics)en_US
dc.subjectRecursive shortest spanning tree methoden_US
dc.subjectVideo-object segmentation algorithmsen_US
dc.subjectImage segmentationen_US
dc.titleUtilization of the recursive shortest spanning tree algorithm for video-object segmentation by 2-D affine motion modelingen_US
dc.typeArticleen_US
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.citation.spage776en_US
dc.citation.epage781en_US
dc.citation.volumeNumber10en_US
dc.citation.issueNumber5en_US
dc.identifier.doi10.1109/76.856454en_US
dc.publisherIEEEen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record