As single layer feature cannot efficiently reduce the disturbances of o cclusion,fast motion and target appearance change on moving object tracking in video surveillance,an algorithm combining the features of pixel and region layer is proposed in this paper.At first,the object and background are coarsely discriminated by the posterior probability of the color feature in pixel level.Then,the candidate r egions are segmented by the superpixel algorithm.Furthermore,accurate distribution of the object is provided by votin g in the superpixel regions with the results of the pixel layer.Finally,the location of the object is obtained by mean shift iteration.And the occlusion is found with the discriminative mask of the pixel and superpixel layer.To ada pt to the change of the object appearance and scene,fused with the detection of occlusion,the histogram of the target and background parts are dynamically updated.Experimental results show that the proposed algorithm is ap plicable to real time moving object tracking in low-contrast scenes and copes with the influence of object occlusio n and fast motion efficiently.