Video object articulation using depth-based content segmentation approaches

Ntalianis, KS; Doulamis, ND; Doulamis, AD; Kollias, SD

dc.contributor.author	Ntalianis, KS	en
dc.contributor.author	Doulamis, ND	en
dc.contributor.author	Doulamis, AD	en
dc.contributor.author	Kollias, SD	en
dc.date.accessioned	2014-03-01T02:49:17Z
dc.date.available	2014-03-01T02:49:17Z
dc.date.issued	2002	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/34471
dc.relation.uri	http://www.scopus.com/inward/record.url?eid=2-s2.0-0036447815&partnerID=40&md5=b17031fae50413a3277f7fb041bd1104	en
dc.subject.other	Algorithms	en
dc.subject.other	Approximation theory	en
dc.subject.other	Color image processing	en
dc.subject.other	Computational geometry	en
dc.subject.other	Feature extraction	en
dc.subject.other	Image analysis	en
dc.subject.other	Special effects	en
dc.subject.other	Constrained fusion of color segments	en
dc.subject.other	Depth-based content segmentation	en
dc.subject.other	Motion geometric space	en
dc.subject.other	Image segmentation	en
dc.title	Video object articulation using depth-based content segmentation approaches	en
heal.type	conferenceItem	en
heal.publicationDate	2002	en
heal.abstract	In this paper two efficient unsupervised video object segmentation approaches are proposed and then extensively compared in terms of computational cost and quality of segmentation results. Both methods exploit depth information. In particular a depth segments map is initially estimated by analyzing a stereo-scopic pair of frames and applying a segmentation algorithm. In the first a ""Constrained Fusion of Color Segments"" (CFCS) in which video object segmentation is performed by fusion of color segments according to a depth similarity criterion. In the second approach firstly a dilated version of the boundary of each depth segment is produced and several feature points are estimated on this dilated boundary. Then for each initial point a normalized Motion Geometric Space (MGS) is created which determines the only allowed way the point can move onto. In the last step each initial point moves onto its MGS and stops according to a weighted stop-function. Experiments on real life stereoscopic sequences are presented to exhibit the speed and accuracy of the proposed schemes.	en
heal.journalName	IEEE International Conference on Image Processing	en
dc.identifier.volume	2	en
dc.identifier.spage	II/417	en
dc.identifier.epage	II/420	en