Unsupervised video-shot segmentation and model-free anchorperson detection for news video story parsing

Xinbo Gao1, Xiaoou Tang1
1Department of Information Engineering, Chinese University of Hong Kong, New Territories, Hong Kong, China

Tóm tắt

News story parsing is an important and challenging task in a news video library system. We address two important components in a news video story parsing system: shot boundary detection and anchorperson detection. First, an unsupervised fuzzy c-means algorithm is used to detect video-shot boundaries in order to segment a news video into video shots. Then, a graph-theoretical cluster analysis algorithm is implemented to classify the video shots into anchorperson shots and news footage shots. Because of its unsupervised nature, the algorithms require little human intervention. The efficacy of the proposed method is extensively tested on more than five hours of news programs.

Từ khóa

#Motion pictures #Gunshot detection systems #Clustering algorithms #Software libraries #Layout #Indexing #Video sequences #Cameras #Video compression #Data mining

Tài liệu tham khảo

wactlar, 1999, new directions in video information extraction and summarization, Proc 10th DELOS Workshop, 1 wactlar, 1996, informedia: news-on-demand experiments in speech recognition, Proc ARPA Speech Recognition Workshop shahraray, 1995, scene change detection and content-based sampling of video sequences, Proc SPIE/IS&amp T Symp Electronic Imaging Science and Technologies Digital Video Compression Algorithms and Technologies, 2419, 2 10.1006/jvci.1996.0030 10.1016/S0031-3203(96)00114-8 10.1109/ICIP.1998.723662 10.1109/2.493456 taniguichi, 1995, an intuitive and efficient access interface to real-time incoming video based on automatic indexing, Proc ACM Multimedia, 25 10.1109/76.825867 swanberg, 1993, knowledge guided parsing and retrieval in video database, Proc SPIE1908, 173 10.1109/MMCS.1996.534992 wactlar, 2000, informedia—search and summarization in the video medium, Proc Imagina 2000 Conf, 1 10.1007/978-1-4615-2277-5 gao, 2000, automatic news video caption extraction and recognition, Lecture Notes in Computer Science 1983, 425, 10.1007/3-540-44491-2_62 10.1109/76.825852 10.1109/MMCS.1995.484921 10.1109/ACV.1996.572007 10.1007/BF01261224 10.1109/76.767124 10.1109/ICIP.1998.727156 hauptmann, 1997, informedia: news-on-demand multimedia information acquisition and retrieval, Intelligent Multimedia Information Retrieval, 213 balakrishnan, 1999, A Textbook of Graph Theory nagasaka, 1992, automatic video indexing and full-search for video appearances, Visual Database Systems, ii, 113 10.1109/ICME.2000.871044 10.1145/266180.266390 boreczky, 1996, comparison of video shot boundary detection techniques, Proc IS&amp T/SPIE Conf Storage and Retrieval for Image and Video Databases IV, spie 2670, 170, 10.1117/12.234794 10.1145/266180.266391 10.1007/978-1-4757-0450-1 10.1109/MMCS.1999.779292 10.1109/76.795057 10.1109/69.755615 10.1145/217279.215080 10.1117/12.131425 10.1109/ADL.1998.670392 10.1145/217279.215068 10.1007/BF01225243 10.1145/244130.244453 10.1007/BF01261227 lam, 1998, video segmentation using color difference histogram, Lecture Notes in Computer Science 1464, 159, 10.1007/BFb0016496 10.1117/12.263440 10.1109/IIS.1997.645332 maybury, 1997, segmentation, content extraction and visualization of broadcast news video using multistream analysis, AAAI Spring Symposium, 1 10.1109/76.475896 10.1109/ICASSP.2001.941191 10.1007/BF01210504 10.1109/T-C.1971.223083 meng, 1995, scene change detection in a mpeg compressed video sequence, Proc SPIE/IS&amp T Symp Electronic Imaging Science and Technologies Digital Video Compression Algorithms and Technologies, 2419