Abstract: The retrieval of the 3D tree models cannot get the higher accuracy, retrieving efficiency and descripting match. In order to solve the problems, a three-dimensional tree model matching method based on tree space is proposed. By constructing the tree space of the three-dimensional tree model dataset, the method computes the difference between the Euclidean distance and the geodesic distance in the tree space by means of spindle matching, contour matching, and branch matching, and gradually matches the corresponding model. The matching implementation results are displayed in the general model dataset and the self-designed model dataset respectively. The method can improve the accuracy of the tree model matching, and is beneficial to the large-scale retrieval and the reuse of 3D tree models.

Key words: tree shape space, tree model dataset, 3D tree model matching, geodesic