On the query of video database

The usefulness of a video database depends on whether the video of interest can be easily located. In this paper, we propose a video retrieval algorithm based on a new representation of video shot. In contrast to key-frame based representation of shot, our approach analyzes all frames within a shot to fully exploit the spatio-temporal information contained in video. A compact shot representation is obtained by integrating the color and spatial features of individual frame. In the video matching step, a shot similarity measure is defined to locate the occurrence of similar video clips in the database. Experimental results indicate that the proposed approach is effective and feasible in retrieving and ranking similar video clips.