Background Information Fusion and its Application in Video Target Tracking

− A Background Information Fusion (BIF) algorithm and its application in video target tracking is proposed in the paper. The BIF algorithm is based on the fact that there are redundant information between different frames. Unlike most of available tracking algorithms based on target features, which focus on the problems of what features the target have, and how does these features change when they moving in a specific scene, The BIF based Target Tracking focus more on the background in which the target existed than available algorithms. We proposed BIF based two step target extraction and tracking algorithm in this paper. At first step, BIF algorithm focus on recovering an intact background from a frame sequences, at the second step it extract target by background differencing algorithm. These two steps algorithms can eliminate the most of the difficulties and challenges in moving target extraction from time-varied background. Our experiments proved that BIF based tracking algorithm is stable, feasible, and effective.