Multiresolution Gradient Vector Flow Field: A Fast Implementation Towards Video Object Plane Segmentation

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

dc.contributor.author	Ntalianis, K	en
dc.contributor.author	Doulamis, N	en
dc.contributor.author	Kollias, S	en
dc.contributor.author	Doulamis, A	en
dc.date.accessioned	2014-03-01T02:49:04Z
dc.date.available	2014-03-01T02:49:04Z
dc.date.issued	2001	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/34284
dc.subject	Depth Map	en
dc.subject	Estimation Method	en
dc.subject	User Interaction	en
dc.subject	Video Object Segmentation	en
dc.subject	Gradient Vector Flow	en
dc.subject	Video Object	en
dc.subject	Video Object Plane	en
dc.title	Multiresolution Gradient Vector Flow Field: A Fast Implementation Towards Video Object Plane Segmentation	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/ICME.2001.1237640	en
heal.identifier.secondary	http://dx.doi.org/10.1109/ICME.2001.1237640	en
heal.publicationDate	2001	en
heal.abstract	In this paper, an efficient scheme for video object segmentation is proposed. The scheme is based on a multiresolution Gradient Vector Flow field (M-GVF) and a Motion Geometric Space (MGS) formulation. In particular the proposed scheme is initialized from an object approximation which can be provided either (a) automatically (unsupervised case) based on a depth map estimation method or (b)	en
heal.journalName	International Conference on Multimedia Computing and Systems/International Conference on Multimedia and Expo	en
dc.identifier.doi	10.1109/ICME.2001.1237640	en