To the problem that object tracking based on single color feature often results in a poor performance in robustness,an improved object tracking algorithm by fusing multiple features is proposed.In order to enhance the important features,an adaptive method of choosing object color histogram is presented to get an accurate color model of the object.Meanwhile,Local Binary Pattern (LBP) operator is used to construct the target texture feature model.Uncertainty measurement method is then introduced into feature fusion to adjust the relative contributions of different features adaptively,and the robustness of the algorithm is significantly enhanced.Experimental results indicate that:Compared with the traditional additive or multiplicative fusion,the proposed method has higher robustness,can implement object tracking in complex scene,and provides a more effective description to the object.