A Moving Target Tracking Algorithm Based on Multi-camera Coordination

Abstract

In this paper, an improved moving target tracking algorithm with multiple cameras based on the FOV line is presented. Firstly, a SIFT algorithm is used to select matching points automatically and generate the FOV line. When the target is through the line, the target’s color histogram matches the real target’s color histogram and endows the best matching with identification to achieve the target handover. Then the Mean Shift algorithm is used to achieve the tracking of the subsequent target. Real-time tracking is carried out. The experimental results show that the algorithm effectively realizes the target continuity tracking among multiple cameras.