Skip to Main Content
The Detection of commercials in news video has been a challenging problem because of the diversity of the commercial programs. In this paper, we propose a novel algorithm for the detection of commercials in news program. In our method, firstly shot transition detection and anchorman shot recognition are conducted, then clustering analysis is employed to label commercial blocks roughly, finally the accurate boundaries of the commercials are marked by monitoring the visual discontinuity of the shots and the average duration of subsequent shots. The experiment results show our algorithm is efficient with high recall and precision rate.