A generic news story segmentation system and its evaluation

The paper presents an approach to segmenting broadcast TV news programmes automatically into individual news stories. We first segment the programme into individual shots, and then a number of analysis tools are run on the programme to extract features to represent each shot. The results of these feature extraction tools are then combined using a support vector machine trained to detect anchorperson shots. A news broadcast can then be segmented into individual stories based on the location of the anchorperson shots within the programme. We use one generic system to segment programmes from two different broadcasters, illustrating the robustness of our feature extraction process to the production styles of different broadcasters.

[1]  B. S. Manjunath,et al.  Representation of motion activity in hierarchical levels for video indexing and filtering , 2002, Proceedings. International Conference on Image Processing.

[2]  Thorsten Joachims,et al.  Making large scale SVM learning practical , 1998 .

[3]  Alan F. Smeaton,et al.  News story segmentation in the Fischlar video indexing system , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).

[4]  Noel E. O'Connor,et al.  Face detection and clustering for video indexing applications , 2003 .

[5]  Yihong Gong,et al.  Automatic parsing of news video , 1994, 1994 Proceedings of IEEE International Conference on Multimedia Computing and Systems.

[7]  Alan F. Smeaton,et al.  The físchlár digital video system: a digital library of broadcast TV programmes , 2001, JCDL '01.

[8]  Stephen W. Smoliar,et al.  Video parsing, retrieval and browsing: an integrated and content-based solution , 1997, MULTIMEDIA '95.