Automatic Segmentation of News Items Based on Video and Audio Features

The automatic segmentation of news items is a key for implementing the automaticcataloging system of news video. This paper presents an approach whichmanages audio and video feature information to automatically segmentnews items. The integration of audio and visual analyses can overcome theweakness of the approach using only image analysis techniques. It makesthe approach more adaptable to various situations of news items. Theproposed approach detects silence segments in accompanying audio, andintegrates them with shot segmentation results, as well as anchor shotdetection results, to determine the boundaries among news items.Experimental results show that the integration of audio and videofeatures is an effective approach to solving the problem of automaticsegmentation of news items.