首页 | 本学科首页   官方微博 | 高级检索  
     检索      

一种用于点云配准的改进迭代最近点算法
引用本文:李运川,王晓红.一种用于点云配准的改进迭代最近点算法[J].教育技术导刊,2009,19(9):175-179.
作者姓名:李运川  王晓红
作者单位:1. 贵州大学 矿业学院;2. 贵州大学 林学院,贵州 贵阳 550025
基金项目:国家自然科学基金项目(31700385);贵州省自然科学基金项目(黔科合 J 字[2014]2070);贵州省科技计划项目(黔科合 LH字[2014]7649)
摘    要:经典的迭代最近点算法(ICP)收敛速度慢,在源点云和目标点云初始姿态不佳时存在容易陷入局部最优解等问题。针对上述问题构建一种结合快速点云粗配准的改进 ICP 算法。改进的 ICP 算法首先利用重心重合法进行两个点云集预处理,缩小平移误差,提高点云重叠度;然后采用随机采样一致性算法(RANSAC)实现两个点云集的粗配准,使两个点云集具有相对较好的初始位置姿态;最后利用体素栅格和 KD 树对 ICP 算法进行改进,实现点云精配准。将改进算法和经典 ICP、GICP 算法进行对比实验,结果表明:相较于经典 ICP 和GICP 算法,改进算法精度更高、速度更快。

关 键 词:点云配准  重心重合  体素栅格  KD    迭代最近点  
收稿时间:2020-01-06

An Improved Iterative Closest Point Algorithm for Point Cloud Registration
LI Yun-chuan,WANG Xiao-hong.An Improved Iterative Closest Point Algorithm for Point Cloud Registration[J].Introduction of Educational Technology,2009,19(9):175-179.
Authors:LI Yun-chuan  WANG Xiao-hong
Institution:1. College of Mining,Guizhou University;2. Forestry College,Guizhou University,Guiyang 550025,China
Abstract:In order to solve the problem of low convergence rate and local optimal solution of the classical iterative closest point algorithm(ICP)when point cloud initial posture is not good,an improved ICP algorithm with fast point cloud initial registration is constructed. Firstly,the two point cloud data sets is preprocessed by center of gravity coincidence,so as to reduce translation error and im? prove point cloud overlap. Then,the random sampling consistency algorithm(RANSAC)is used to realize the initial registration of two point cloud sets to acquire a better initial position and posture. Finally,the voxel grid and KD tree are used to improve the ICP algorithm to achieve accurate registration of point clouds. The experimental results show that the improved algorithm has better accuracy and speed than the classical ICP and GICP algorithms.
Keywords:center of gravity coincidence  RANSAC  voxel grid  KD tree  ICP  
点击此处可从《教育技术导刊》浏览原始摘要信息
点击此处可从《教育技术导刊》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号