A bandwidth-adaptive tracking algorithm based on Kalman-mean shift method is proposed.Firstly，the starting position of mean shift is predicted by Kalman filter at present，and then a scale updating item of tracking window is appended in the mean shift algorithm based on the relation between mutual information and the object scale.Through the scale updating,the moving object,especially the object of scale variance,is adaptively tracked.Experimental results demonstrate that the adaptability of mean shift method is enhanced by the improved algorithm,which is effectively applied in the tracking problem for the object of scale variance in the process of long time tracking.