Research of Mean Shift target tracking with Spatiogram Corrected Background-Weighted Histogram

Abstract

For traditional mean shift tracking algorithm based on histogram, tracking is failing when target appears under the complicated tracking conditions. It can't significantly distinguish color-similar targets and backgrounds. This thesis proposed a kind of Mean Shift tracking algorithm based on Spatiogram Corrected Background Weighted Histogram and offered detailed derivation of the new algorithm. It can enhance targeting positioning by reducing background prominent feature in target models. Its experiment shows that the algorithm can effectively track the targets on complicated situations of occlusion and illumination variations. It improved the limitations that traditional Mean Shift template can't be updated.