A Motion-Location Based Indexing Method for Retrieving MPEG Videos

Many content-based video data indexing and retrieval systems have utilized the syntactic contents of the video sequences such as color, texture, and shape. And only a few researches have addressed indexing and retrieving video data by motion. In this paper, we present a method to automatically compute motionbased indexes for video units and to retrieve video units using motion information. Since videos are full of motion and the eld of motion is the whole frame, we propose a method to divide this eld of motion into several sub elds and extract the motion features of every sub eld. As a result, location information will be added to the motion vectors. Three keyframes will be extracted as representative frames for the corresponding shot, rst, last, and middle frame. Then, the system extracts the MPEG coded motion vectors information of the macroblocks of the representative frames and use these information to compute the motion indexes of the corresponding shots. This method is faster than other methods since motion vectors have already been computed by the MPEG software. Motions that result from camera movement and objects movements are distinguished. As a result, users are able to issue queries based on either type of motion.