基于下采样优化的点云配准方法
Point Cloud Registration Method Based on Down Sampling Optimization
王明 1邓志良 2严飞 2刘佳2
作者信息
- 1. 南京信息工程大学自动化学院,江苏南京 210044
- 2. 南京信息工程大学自动化学院,江苏南京 210044;江苏省大气环境与装备技术协同创新中心,江苏南京 210044
- 折叠
摘要
针对点云数据量庞大导致配准效率低下以及部分空间结构复杂易产生误匹配等问题,提出一种基于精简点云优化粗配准的点云配准算法.在体素下采样的基础上根据邻域点到中心点法线的角度均值差提取关键点;采用快速点特征直方图(FPFH)作为特征描述子;并在对应关系查找方面,根据邻近匹配对之间向量夹角的相似性结合随机抽样一致性(RANSAC)算法进行筛选优化,精确对应关系,完成粗配准;最后通过ICP算法实现精配准.实验结果表明,在点云表面空间变化差异较大的地方,所提算法能够有效地提取关键点,良好的对应关系为后续精配准提供了较好的初始位姿,有效地缩短了点云配准时间.
Abstract
This paper addresses the challenges of inefficient registration in point cloud data processing due to volume and com-plexity of spatial structures by introducing an optimized point cloud registration algorithm.The algorithm integrates a refined point cloud with an initial rough registration step.Key points are identified through voxel sampling,leveraging the variance in mean angles between neighborhood points and the center point normal line.The Fast Point Feature Histogram(FPFH)serves as the feature descriptor.In the search of correspondence relationship,according to the similarity of vector angle between adja-cent matching pairs and Random Sampling Consistency(RANSAC)algorithm,filtering optimization is carried out to accurate-ly correspond to the relationship and complete rough registration.Finally,the ICP algorithm is used to achieve accurate regis-tration.The results show that the proposed algorithm effectively captures key points in regions of significant spatial variation,providing an advantageous initial position for precise registration and significantly reducing overall point cloud registration time.
关键词
机器视觉/点云配准/关键点提取/特征匹配Key words
machine vision/point cloud registration/key point extraction/feature matching引用本文复制引用
基金项目
江苏省产业前瞻与关键核心技术重点项目(BE2020006-2)
出版年
2024
NETL
NSTL
万方数据