| Application of the video information is more and more extensive, such as shopping online, video web, VOD and digital library, etc. The technology among them is mainly concentrated on these respects: video compressing, transmitting, management, control and searching, etc. Because video information is heavy, and abundant in content, video effective management and search becomes a difficult subject. Today, the management and search of video is done mainly based on video file and its describing, which can't operate from the intra content of video, however, it is usually what the user cares. So occur a new field about video processing: Content Based Video Retrieval (CBVR). Content-based Video Retrieval is a newly arisen technique in information retrieval of multimedia database. It extracts object semantic features straight from video data, such as: image color, texture, shape, shot, scene, shot motion, etc. Then search and retrieval similarity video data from a lot of video streams in database based these feature. This paper have done the following groundwork around this field: 1,In the first part, the application,system constitutes,and respective function of Content-based Video Retrieval are discussed briefly and firstly. Then summarize the theory, merit and demerit of the arithmetic of classic key-frame extraction. This paper is based on these content. 2,In the second part, mainly discuss the two-dimension motion estimation technique. Based on block-matching motion estimation, this chapter introduce the theory of block-matching and matching criteria, studied several important fast search arithmetic in detail. At the same time, it make a comparison and analysis of predicted performance among them and give some experiment results. The content in this part is very important, it is the one of the main research work in this paper. All of the other work later are launched on these content. 3,In the third part,mainly discuss one of the emphases of this paper: key-frame extraction arithmetic of the Video Sequence based on the maximal... |
