A multiscale tree-structure for fast browsing and effective transmission of video files

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

dc.contributor.author	Ntalianis, KS	en
dc.contributor.author	Doulamis, ND	en
dc.contributor.author	Doulamis, AD	en
dc.contributor.author	Koukoutsidis, IZ	en
dc.contributor.author	Kollias, SD	en
dc.date.accessioned	2014-03-01T02:41:39Z
dc.date.available	2014-03-01T02:41:39Z
dc.date.issued	2001	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/30585
dc.subject	Cross Correlation	en
dc.subject	Tree Structure	en
dc.subject	Full Resolution	en
dc.subject	layer 2	en
dc.subject	layer 3	en
dc.subject.other	Content based retrieval	en
dc.subject.other	Correlation methods	en
dc.subject.other	Feature extraction	en
dc.subject.other	Real time systems	en
dc.subject.other	Trees (mathematics)	en
dc.subject.other	Vector quantization	en
dc.subject.other	Video files	en
dc.subject.other	Video signal processing	en
dc.title	A multiscale tree-structure for fast browsing and effective transmission of video files	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/MMSP.2001.962779	en
heal.identifier.secondary	http://dx.doi.org/10.1109/MMSP.2001.962779	en
heal.publicationDate	2001	en
heal.abstract	In this paper, a multiscale video content organization scheme is proposed for fast browsing and efficient transmission of video sequences. The scheme leads to construction of a five-layer tree structure. At layer 0 the root-node is located, connected to all nodes of layer 1, each corresponding to a class of shots. Then every class of shots is expanded at layer 2. The nodes of this layer represent shots. At the next resolution level (layer 3) nodes represent key-frames of shots. Finally at layer 4 the full resolution level is reached, where nodes correspond to frames of the sequence. Each node contains a viewing element and we focus on the extraction of these elements for layers 1,2 and 3. Viewing elements of layers 1 and 3 are optimally extracted by minimizing a cross correlation criterion. Additionally viewing elements of layer 2 are selected according to a correlation measure between the mean vector of a shot and each of the frames within this shot. The resulting tree-structure enables a user to quickly and easily detect content of interest, by selecting the viewing element of his/her liking. Experimental results on real-life video sequences indicate the promising performance of the proposed scheme.	en
heal.journalName	2001 IEEE Fourth Workshop on Multimedia Signal Processing	en
dc.identifier.doi	10.1109/MMSP.2001.962779	en
dc.identifier.spage	479	en
dc.identifier.epage	484	en