Tracking multiple moving objects under complex scenes is the key problem in v isual surveillant system.When objects are occluded,two-dimensional infor mation of objects can be lost easily,which will make the system can′t track and recognize objects.In this paper,the three-dimensi onal visual information is proposed by Kinect camera,which is used for building three-dimensional layered graph mo del form three different fields containing vertex,edge and spatial structure.The features of vertex,edge and spatial structure of three-dimensional layered graph model are matched between two consecutive frame s separately,and the three-dimensional layered graph model are also matched by these vertex,edge an d spatial structures.Then,the matching method is computed between consecutive frames by the three-dimensional layered models of different objects to track objects.When the objects are occluded,the clusters of the occ lusion region are matched with the features of three-dimensional layered graph model to get the matching results, then the tracking results are determined even under occlusions.The experimental results show that the performa nce of proposed method is better than traditional method on the image sequences using Kinect camera even u nder occlusions,and the tracking performance rates are improved by 3%,which in dicates that our method can track the multiple object better even under complex scenes.