A New Approach For High Level Video Structuring

This paper introduces a high level video structuring scheme using both of color and motion features. Until now, the color information is used for the video scene segmentation researches. However, the action movies having rapid motion of objects have characteristics of dynamic changes of color information. In this case, the traditional approach is not so appropriate. To overcome this drawback, a new criterion for Video shot similarity using color and motion features is presented and discussed. Then, a new adaptive scene segmentation algorithm is proposed, of which main features include adaptive weighting of color and motion similarity between two shots. Moreover, the improved overlapping links scheme is proposed for reducing the time cost for shot grouping. The proposed scheme is evaluated using movie of Terminator II together with implementing prototype video browsing system using the structured video.