Title :
AnchorClu: An Anchorperson Shot Detection Method Based on Clustering
Author :
Luan, Xi-Dao ; Xie, Yu-Xiang ; Wu, Ling-Da ; Wen, Jun ; Lao, Song-Yang
Author_Institution :
National University of Defense Technology, Changsha, China
Abstract :
Anchorperson shot detection is an effective way of news video structuring. According to some features of anchorperson shots, such as visually similar with each other, long duration, and large span, etc., an anchorperson shot detection method based on clustering called AnchorClu is proposed. After fast clustering of shots’ key frames, some clusters including the anchorperson cluster can be got. Then by some proper rules, the anchorperson cluster is selected out, and the anchorperson shots can also be extracted to help the analysis of news video structuring. Experiments prove the effectiveness of the method, which is fast and gets the average recall of 93% and the average precision of 98%.
Keywords :
Broadcast technology; Distributed computing; Electronic mail; Feature extraction; Gunshot detection systems; Image edge detection; Multimedia communication; Skin; TV broadcasting; Visual perception;
Conference_Titel :
Parallel and Distributed Computing, Applications and Technologies, 2005. PDCAT 2005. Sixth International Conference on
Print_ISBN :
0-7695-2405-2
DOI :
10.1109/PDCAT.2005.90