Please use this identifier to cite or link to this item:
Title: An efficient scene break detection based on linear prediction
Authors: Cai, C
Lam, KM 
Tan , Z
Issue Date: 2004
Source: Proceedings of the International Symposium on Intelligent Multimedia, Video and Speech Processing (ISIMP’2004), Hong Kong, 20-22 Oct. 2004, p. 555-558
Abstract: Detection of edits in a video sequence is the first step for video analysis, which segments a video into its basic components. In this paper, we propose a novel and efficient approach to scene break detection, which can detect cuts, dissolves, and fades reliably. Our approach is based on the temporal linear prediction of the frames. For the frames in a video shot, a frame can be predicted from its previous frames. If the prediction error is high, a cut should happen. For dissolves and fades, the prediction coefficients are constants, and these kinds of gradual transitions can be detected by comparing the prediction errors of two different linear predictions. Experimental results show that our algorithm can achieve high precision even if a video contains object motion and camera motion, and is able to detect and classify cuts, dissolves and fades in real time.
Keywords: Video signal processing
ISBN: 0-7803-8687-6
DOI: 10.1109/ISIMP.2004.1434124
Appears in Collections:Conference Paper

View full-text via PolyU eLinks SFX Query
Show full item record


Last Week
Last month
Citations as of Sep 22, 2020

Page view(s)

Last Week
Last month
Citations as of Sep 22, 2020

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.