To prevent moving shadow from being misunderstood as part of moving objects in video target segmentation,a novel approach is proposed for the shadow detection.Firstly,video target segmentation was achieved through background subtraction based on adaptive Gaussian mixture models.Then,based on the observation that shadow regions present similar textural characteristics in each frame of the gray-level video-sequence and in the corresponding adaptive background model,the shadow was detected based on the similarity of texture represented by histogram of "uniform" patterns of Local Binary Patterns(LBP) between shadow region and corresponding region in the background.The approach requires only a small number of parameters,and experiments on variety real-world video data demonstrate the favorable performance and robustness of the proposed scheme.It can be applied to moving target segmentation,detection and etc.