This paper presents a real-time color image tracking method. In order to implement an effective and robust tracking task

a novel approach of weighted color target model based on color histogram is discussed

It takes into account the targets shape and position of pixels as necessary factors in target model. This makes the description of targets feature more reasonable. Furthermore

the starting position of target is found with Kalman filter in every frame

and then mean shift is utilized to track the target position.Experiment result shows

in Contrast with mean shift

the proposed method can locate object more accurately and have lower complication of calculation.The proposed method is more robust，especially for some complex tracking conditions such as occultation and object which is moving fast.