Combining Audio-Based and Video-Based Shot Classification Systems for News Videos Segmentation

In this paper we propose an innovative combination strategy for a system using video and audio stream of a news video to automatically segment it into stories. In our approach, the segmentation is performed in two steps: first, shots are classified by combining three different anchor shot detection algorithms using video information only. Then, the shot classification is improved by using a novel anchor shot detection method based on features extracted from the audio track. Experimental results demonstrate that the combined use of audio and video allows our system to perform better than approaches based only on video information in terms of both shot classification and news story segmentation.