Adaptable neural networks for unsupervised video object segmentation of stereoscopic sequences

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

dc.contributor.author	Doulamis, AD	en
dc.contributor.author	Ntalianis, KS	en
dc.contributor.author	Doulamis, ND	en
dc.contributor.author	Kollias, SD	en
dc.date.accessioned	2014-03-01T01:16:05Z
dc.date.available	2014-03-01T01:16:05Z
dc.date.issued	2001	en
dc.identifier.issn	0302-9743	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/13915
dc.subject	Adaptive Neural Network	en
dc.subject	Convex Function	en
dc.subject	Linear Constraint	en
dc.subject	Object Extraction	en
dc.subject	Video Object Segmentation	en
dc.subject.classification	Computer Science, Theory & Methods	en
dc.subject.other	IMAGES	en
dc.title	Adaptable neural networks for unsupervised video object segmentation of stereoscopic sequences	en
heal.type	journalArticle	en
heal.identifier.primary	10.1007/3-540-44668-0_147	en
heal.identifier.secondary	http://dx.doi.org/10.1007/3-540-44668-0_147	en
heal.language	English	en
heal.publicationDate	2001	en
heal.abstract	An adaptive neural network architecture is proposed in this paper, for efficient video object segmentation and tracking in stereoscopic sequences. The scheme includes: (A) A retraining algorithm that optimally adapts the network weights to the cur-rent conditions and simultaneously minimally degrades the previous network knowledge, (B) A semantically meaningful object extraction module for constructing the retraining set of the current conditions and (C) a decision mechanism, which detects the time instances when network retraining is required. The retraining algorithm results in the minimization of a convex function subject to linear constraints. Furthermore description of the current conditions is achieved by appropriate combination of color and depth information. Experimental results on real life video sequences indicate the promising performance of the proposed adaptive neural network-based video object segmentation scheme.	en
heal.publisher	SPRINGER-VERLAG BERLIN	en
heal.journalName	ARTIFICIAL NEURAL NETWORKS-ICANN 2001, PROCEEDINGS	en
heal.bookName	LECTURE NOTES IN COMPUTER SCIENCE	en
dc.identifier.doi	10.1007/3-540-44668-0_147	en
dc.identifier.isi	ISI:000173024600146	en
dc.identifier.volume	2130	en
dc.identifier.spage	1060	en
dc.identifier.epage	1066	en