Tube-embodied gradient vector flow fields for unsupervised video object plane (VOP) segmentation

Doulamis, A; Doulamis, N; Kollias, S; Ntalianis, K

dc.contributor.author	Doulamis, A	en
dc.contributor.author	Doulamis, N	en
dc.contributor.author	Kollias, S	en
dc.contributor.author	Ntalianis, K	en
dc.date.accessioned	2014-03-01T02:49:07Z
dc.date.available	2014-03-01T02:49:07Z
dc.date.issued	2001	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/34309
dc.subject	Active Contour	en
dc.subject	Gradient Vector Flow	en
dc.subject	Video Object Plane	en
dc.title	Tube-embodied gradient vector flow fields for unsupervised video object plane (VOP) segmentation	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/ICIP.2001.958574	en
heal.identifier.secondary	http://dx.doi.org/10.1109/ICIP.2001.958574	en
heal.publicationDate	2001	en
heal.abstract	In this paper constrained Gradient Vector Flow (GVF) field generation is performed, for fast and accurate unsupervised stereoscopic semantic segmentation. The scheme utilizes the in- formation provided by a depth segments map, produced by stereo analysis methods and incorporation of a segmentation algorithm. Then a Canny edge detector is applied to the depth region and produces an edge map. The	en
heal.journalName	Image Processing, IEEE International Conference	en
dc.identifier.doi	10.1109/ICIP.2001.958574	en