Unsupervised stereoscopic video object segmentation based on active contours and retrainable neural networks

Ntalianis, K; Doulamis, A; Doulamis, N

dc.contributor.author	Ntalianis, K	en
dc.contributor.author	Doulamis, A	en
dc.contributor.author	Doulamis, N	en
dc.date.accessioned	2014-03-01T01:52:02Z
dc.date.available	2014-03-01T01:52:02Z
dc.date.issued	2002	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/26535
dc.relation.uri	http://www.scopus.com/inward/record.url?eid=2-s2.0-4944239425&partnerID=40&md5=36264082c6d571d910eeb2123ea0f94e	en
dc.subject	Active contours	en
dc.subject	Adaptive neural networks	en
dc.subject	Depth based segmentation	en
dc.subject	MPEG-4	en
dc.subject	Video objects	en
dc.subject.other	Algorithms	en
dc.subject.other	Image segmentation	en
dc.subject.other	Information analysis	en
dc.subject.other	Knowledge acquisition	en
dc.subject.other	Multimedia systems	en
dc.subject.other	Performance	en
dc.subject.other	Vectors	en
dc.subject.other	Active contours	en
dc.subject.other	Adaptive neural networks	en
dc.subject.other	Depth based segmentation	en
dc.subject.other	MPEG-4	en
dc.subject.other	Video objects	en
dc.subject.other	Neural networks	en
dc.title	Unsupervised stereoscopic video object segmentation based on active contours and retrainable neural networks	en
heal.type	journalArticle	en
heal.publicationDate	2002	en
heal.abstract	In this paper an unsupervised scheme for stereoscopic video object extraction is presented based on a neural network classifier. More particularly, the procedure includes: (A) A retraining algorithm for adapting neural network weights to current conditions and (B) An active contour module, which extracts the retraining set. The retraining algorithm takes into consideration both the former and the current network knowledge in order to achieve good generalization and reduce retraining time. The retrained network performs video object tracking to the rest of the frames within a shot. Retraining set extraction is accomplished by utilizing depth information, provided by stereoscopic video analysis and incorporating an active contour. Finally results are presented which illustrate the promising performance of the proposed approach in real life experiments.	en
heal.publisher	World Scientific and Engineering Academy and Society	en
heal.journalName	Recent Advances in Circuits, Systems and Signal Processing	en
dc.identifier.spage	374	en
dc.identifier.epage	379	en