中图法分类号TP317.4文献标识码A文章编号颅骨点云模型的局部.doc

中图法分类号: TP317.4 文献标识码:A 文章编号: 颅骨点云局部特征配准 赵夫群1,2 1.咸阳师范学院教育科学学院，陕西 咸阳 712000；2.西北大学信息科学与技术学院，陕西 西安 710127信息科学与技术学院， 摘 要：颅面复原，提出一种基于局部特征的点云配准。首先提取点云的局部深度、法线偏角和点云密度等局部特征然后计算局部特征集的相关性，得到相关候选点集通过删减外点粗配准最后采用基于和动态迭代系数的改进迭代最近点 (iterative closest point, ICP) 算法实现的细配准。结果表明基于局部特征的点云配准算法可以点云的精确配准，iterative closest point, PCP) 算法相比，其配准精度差异不大，收敛速度提高了约50%。结论 因此说，基于局部特征的点云配准算法不仅可以用于公共点云数据模型的精确配准，而且更适用于颅骨点云数据模型的配准，是一种精度高、速度快的 关键词：配准；局部特征；迭代最近点；；动态迭代系数 Local feature registration method of skull point cloud model Zhao Fuqun1,2，Zhou Mingquan2,3，Geng Guohua2 1. College of Education Science, Xianyang Normal University, Xianyang 712000;2.College of Information Science and Technology, Northwest University, Xian 710127，China; 3. College of Information Science and Technology, Beijing Normal University, Beijing 100875，China. Abstract: Objective: Point cloud registration is a crucial and active research topic in computer vision with numerous applications including 3D modeling, object recognition, scene understanding, 3D shape detection, craniofacial reconstruction and so on. 3D scanner can only obtain a partial 3D point cloud of one object associated with a single coordinate system from one viewpoint. In order to reconstruct the whole 3D shape, the 3D point clouds captured from different viewpoints must be transformed into a common coordinate system according to rigid transformations. The aim of 3D point cloud registration is to compute the rigid transformation between 3D point clouds and get the complete 3D shape of the object automatically. Skull registration is one of an important step in craniofacial reconstruction, and the correctness of its registration will directly affects the result of craniofacial reconstruction. Skull registration is the process of searching one or more reference skulls from the existing skull database which is most similar to a unknown skull. The face of the reference skull can be used as the reference face of the unknown skull, so as to provide