Shot change detection with adaptive thresholds

Shot change detection is one of the critical techniques in video browsing and indexing system. In this paper, we propose a shot change detection algorithm with adaptive thresholds on DC images. The bit-rate information is used to decrease the number of I frames that take part in the shot change detection. Then, local adaptive thresholds are obtained based on the main color of a segment of the video sequence. Finally, shot changes are detected based on modified twin-comparison method. Experimental results show that our algorithm can detect shot change detection from long video sequence with reduced computation complexity, and at the same time solve the problems caused by object moving and camera panning in the shot change detection.