Title :
Camera Motion Detection for Conversation Scenes in Movies
Author :
Jiayin, Liu ; Chuang, Wang ; Kim, Jae Ho
Author_Institution :
Dept. of Electron. Eng., Pusan Nat. Univ., Pusan, South Korea
Abstract :
In this paper, camera movements including zoom, pan and tilt could be efficiently detected for conversation scenes in movies using an improved feature point matching method. RANSAC algorithm is applied to reduce the error rate of feature matching. This implementation possesses notable significance for conversation scenes´ editing and analysis. Besides, it is an essential fundamental step for constructing a visual attention model.
Keywords :
image matching; motion compensation; video signal processing; RANSAC algorithm; camera motion detection; conversation scenes; feature point matching; movies; visual attention model; Algorithm design and analysis; Cameras; Feature extraction; Histograms; Motion detection; Motion pictures; Visualization; RANSAC; camera motion; conversation scenes; feature matching; movie analysis;
Conference_Titel :
Computational and Information Sciences (ICCIS), 2010 International Conference on
Conference_Location :
Chengdu
Print_ISBN :
978-1-4244-8814-8
Electronic_ISBN :
978-0-7695-4270-6
DOI :
10.1109/ICCIS.2010.180
