An efficient fully unsupervised video object segmentation scheme using an adaptive neural-network classifier architecture

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

dc.contributor.author	Doulamis, A	en
dc.contributor.author	Doulamis, N	en
dc.contributor.author	Ntalianis, K	en
dc.contributor.author	Kollias, S	en
dc.date.accessioned	2014-03-01T01:18:38Z
dc.date.available	2014-03-01T01:18:38Z
dc.date.issued	2003	en
dc.identifier.issn	1045-9227	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/15120
dc.subject	Adaptive neural networks	en
dc.subject	MPEG-4	en
dc.subject	Video object extraction	en
dc.subject.classification	Computer Science, Artificial Intelligence	en
dc.subject.classification	Computer Science, Hardware & Architecture	en
dc.subject.classification	Computer Science, Theory & Methods	en
dc.subject.classification	Engineering, Electrical & Electronic	en
dc.subject.other	Adaptive systems	en
dc.subject.other	Algorithms	en
dc.subject.other	Approximation theory	en
dc.subject.other	Color image processing	en
dc.subject.other	Decision theory	en
dc.subject.other	Feature extraction	en
dc.subject.other	Image compression	en
dc.subject.other	Image segmentation	en
dc.subject.other	Motion estimation	en
dc.subject.other	Object recognition	en
dc.subject.other	Video conferencing	en
dc.subject.other	Video signal processing	en
dc.subject.other	Adaptive neural network	en
dc.subject.other	Motion picture experts group	en
dc.subject.other	Tracking module	en
dc.subject.other	Video object extraction	en
dc.subject.other	Video object segmentation	en
dc.subject.other	Neural networks	en
dc.title	An efficient fully unsupervised video object segmentation scheme using an adaptive neural-network classifier architecture	en
heal.type	journalArticle	en
heal.identifier.primary	10.1109/TNN.2003.810605	en
heal.identifier.secondary	http://dx.doi.org/10.1109/TNN.2003.810605	en
heal.language	English	en
heal.publicationDate	2003	en
heal.abstract	In this paper, an unsupervised video object (VO) segmentation and tracking algorithm is proposed based on an adaptable neural-network architecture. The proposed scheme comprises: 1) a VO tracking module and 2) an initial VO estimation module. Object tracking is handled as a classification problem and implemented through an adaptive network classifier, which provides better results compared to conventional motion-based tracking algorithms. Network adaptation is accomplished through an efficient and cost effective weight updating algorithm, providing a minimum degradation of the previous network knowledge and taking into account the current content conditions. A retraining set is constructed and used for this purpose based on initial VO estimation results. Two different scenarios are investigated. The first concerns extraction of human entities in video conferencing applications, while the second exploits depth information to identify generic VOs in stereoscopic video sequences. Human face/body detection based on Gaussian distributions is accomplished in the first scenario, while segmentation fusion is obtained using color and depth information in the second scenario. A decision mechanism is also incorporated to detect time instances for weight updating. Experimental results and comparisons indicate the good performance of the proposed scheme even in sequences with complicated content (object bending, occlusion).	en
heal.publisher	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC	en
heal.journalName	IEEE Transactions on Neural Networks	en
dc.identifier.doi	10.1109/TNN.2003.810605	en
dc.identifier.isi	ISI:000182980300012	en
dc.identifier.volume	14	en
dc.identifier.issue	3	en
dc.identifier.spage	616	en
dc.identifier.epage	630	en