DocumentCode :
3435236
Title :
A fast shot-boundary detection based on K-step slipped window
Author :
Qin, Tuanfa ; Gu, Jiayu ; Chen, Huiting ; Tang, Zhenhua
Author_Institution :
Sch. of Comput. & Electron. Inf., Guangxi Univ., Nanning, China
fYear :
2010
fDate :
24-26 Sept. 2010
Firstpage :
190
Lastpage :
195
Abstract :
In order to improve the efficiency and precision of gradual transition detection in the recent method of shot-boundary detection, in this paper, a fast shot-boundary detection method based on K-step slipped window by considering the low-feature and edit-feature of the video-shot sufficiently is proposed. First, it selects the candidates of the shot-boundary by K-step slipped window and adaptive thresholds, and then, it does hard cut detection, flash exclusion and gradual transition detection orderly. This paper compares its experiment results to the existing LTD method, the results show that our methods´ calculated amount is the most amount of LTD´s 1/3 and our method has the higher precision.
Keywords :
video signal processing; K-step slipped window; adaptive threshold; fast shot-boundary detection; flash exclusion; gradual transition detection; video shot; Accuracy; Cameras; Feature extraction; Motion compensation; Pixel; Streaming media; Video sequences; K-step slipped window; adaptive thresholds; gradual transition detection; hard cut detection;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Network Infrastructure and Digital Content, 2010 2nd IEEE International Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4244-6851-5
Type :
conf
DOI :
10.1109/ICNIDC.2010.5657841
Filename :
5657841
Link To Document :
بازگشت