改进的ICP点云配准算法  

Improved ICP Algorithm for Point Cloud Registration

作　　者：朱新宇 万剑华[1] 刘善伟[1] 曾喆[1] 

机构地区：[1]中国石油大学(华东)地球科学与技术学院,山东青岛266580

出　　处：《海洋测绘》2015年第2期77-79,共3页Hydrographic Surveying and Charting

摘　　要：三维激光点云配准是点云三维建模的关键问题之一。经典的ICP算法对点云初始位置要求较高且配准效率较低,提出了一种改进的ICP点云配准算法。该算法首先利用主成分分析法实现点云的初始配准,获得较好的点云初始位置,然后在经典ICP算法的基础上,采用k-d tree结构实现加速搜索,并利用方向向量夹角阈值去除错误点对,提高算法的效率。实验表明,本算法流程在保证配准精度的前提下,显著提高了配准效率。The registration of 3D laser point cloud is one of the key problems in 3D modeling. According to the classical ICP algorithm,the paper proposes an improved ICP algorithm for point cloud registration. First of all,the initial registration in this paper uses principal component analysis method to obtain a better initial position of the point cloud. Then two point clouds are registered by k-d tree search and angle between the direction vectors of two the point clouds based on traditional ICP algorithm. The accuracy of the improved process of algorithm will not be affected to improve the efficiency. The algorithm is verified in the applications.

关 键 词：点云配准 迭代最近点算法 主成分分析 方向向量阈值 k-d TREE 

分 类 号：P237[天文地球—摄影测量与遥感]