High speed tracking algorithm of moving object

In this paper, the authors suggest that a high-speed tracking algorithm for a moving object is separated from the background, using partial boundary line information. They extract a moving vector on the input image which has environmental variation, using high-performance BMA, and they extract the moving object on the basis of the moving vector. Next, they extract a boundary line on the moving object as an initial feature-vector generating step for the moving object. As a result, the simulation for the proposed algorithm shows that BMA operation is reduced about 39% in real images and tracking error is less than 2 pixels when the feature vector is [10/spl times/5] by using the information of every directional boundary line.