基于光流场估计的自适应Mean-Shift算法及其目标跟踪应用

he traditional Mean-Shift algorithm often fails when tracking a target with a high speed, a large change of scale or an occlusion. To tackle the problem, the article proposes an adaptive Mean-Shift algorithm. This method is based on the mean drift vector of the tracking window center, and Bhattacharyya coefficient based dichotomy is used to get both width and height of the window. Especially, Optical Flow method is employed to fine-tune the window position and window size according to the information of feature points. In tracking targets which are occluded by immobile objects, the article uses the color difference to observe the occlusion zone, and catches the target with Bhattacharyya coefficient when it is unsheltered. Experiments show that the tracking algorithm has a very good effect in some cases, and the good effect is also further confirmed by a practical application