| 本文已被：浏览 4814次 下载 8825次 |
码上扫一扫！ |
|
|
| 3D点云形状特征的二维主流形描述 |
|
孙晓鹏1,2, 王冠1, 王璐1, 魏小鹏3,4
|
|
1.辽宁师范大学 计算机与信息技术学院 计算机系统研究所, 辽宁 大连 116029;2.北京邮电大学 智能通信软件与多媒体北京市重点实验室, 北京 100876;3.大连理工大学 机械工程学院, 辽宁 大连 116024;4.辽宁省先进设计与智能计算省部共建教育部重点实验室大连大学, 辽宁 大连 116622
|
|
| 摘要: |
| 首先,对空间分布不均匀且无序的三维点云构造其二维主流形,并以与球面同胚的封闭曲面网格形式给出其二维主流形的二次优化逼近,以主流形网格有序均匀的结点分布表示三维点云空间分布无序且不均匀的形状特征,降低了三维形状描述的难度;然后,以基本几何变换作为快速粗对齐、以迭代最近法向点(ICNP)方法作为精准对齐,确定两个主曲面网格之间最佳刚性变换,ICNP方法在寻找最近点时考虑法向夹角,利用了更多的几何信息,实现快速精准的刚性对齐,兼顾计算精度和速度;最后,以对齐误差作为两个3D点云之间形状差异测度.实验结果表明:所提出的基于主流形二次曲面网格优化逼近的三维点云模型形状描述方法对三维点云的分辨率和噪声等干扰因素具有较高的健壮性,可以用于三维检索的形状描述. |
| 关键词: 形状特征 二维主流形 网格优化逼近 三维检索 ICNP |
| DOI：10.13328/j.cnki.jos.004653 |
| 分类号: |
| 基金项目:国家自然科学基金(60873110, 61170143, 61472170); 智能通信软件与多媒体北京市重点实验室开发课题(ITSM201301) |
|
| 3D Point Cloud Shape Feature Descriptor Using 2D Principal Manifold |
|
SUN Xiao-Peng1,2, WANG Guan1, WANG Lu1, WEI Xiao-Peng3,4
|
|
1.Institute of Computer System, Department of Computer and Information Technology, Liaoning Normal University, Dalian 116029, China;2.Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia, Beijing University of Posts and Telecommunications, Beijing 100876, China;3.School of Mechanical and Engineering, Dalian University of Technology, Dalian 116024, China;4.Key Laboratory of Advanced Design and Intelligent Computing of Ministry of Education Dalian University, Dalian 116622, China
|
| Abstract: |
| This paper first construct 2D principal manifold of the 3D point cloud which is typically unoriented and unevenly distributed in space, and give the quadratic optimized approximation of principal manifold in form of watertight mesh with spherical homeomorphism. By this method, the shape description of 3D point cloud is converted into the description of 2D principal manifold evenly spread in spherical parameter field. Then, it applies translation, rotation and scaling to the quadratic optimized mesh to align the mesh polar axis, denoting this process as initial rough alignment. Finally, the ICNP (iterative closest normal point) algorithm is used to iteratively refine the rigid transformation to bring the two meshes into the best alignment with respect to the least mean square error, and the alignment error is recorded as difference distance between two 3D point clouds. The experimental results show that the proposed 3D point cloud shape description based on quadratic optimized approximation of 2Dprincipal manifold is robust to noise and resolution, and can be used as the shape descriptor for 3D retrieval. |
| Key words: shape feature 2D principal manifold optimized mesh approximation 3D shape retrieval ICNP |
