计算机应用 ›› 2012, Vol. 32 ›› Issue (03): 762-765.DOI: 10.3724/SP.J.1087.2012.00762

• 图形图像技术 • 上一篇    下一篇

邻域特征在点云配准中的应用

贺永兴1,欧新良2,匡小兰3   

  1. 1.湖南工业大学 计算机与通信学院,湖南 株洲 412008;
    2.长沙学院 计算机科学与技术系,长沙 410003;
    3.长沙商贸旅游职业技术学院 计算机科学与技术系,长沙 410003
  • 收稿日期:2011-09-23 修回日期:2011-10-10 发布日期:2012-03-01 出版日期:2012-03-01
  • 通讯作者: 贺永兴
  • 作者简介:贺永兴(1984-),男,新疆乌鲁木齐人,硕士研究生,主要研究方向:计算机图形学、计算机辅助几何设计;欧新良(1965-),男,湖南桃江人,教授,博士,主要研究方向:计算机图形学、计算机辅助几何设计;匡小兰(1980-),女,湖南祁东人,讲师,硕士,主要研究方向:计算机图形学、计算机辅助几何设计。
  • 基金资助:

    湖南省自然科学基金资助项目(07JJ3121);湖南省教育厅科技重点项目(09A010)。

Application of neighborhood feature in point cloud registration

HE Yong-xing1, OU Xin-liang2, KUANG Xiao-lan3   

  1. 1.College of Computer and Communication, Hunan University of Technology, Zhuzhou Hunan 412008, China;
    2.Department of Computer Science and Technology, Changsha University, Changsha Hunan 410003, China;
    3.Department of Computer Science and Technology, Changsha Commerce and Tourism College, Changsha Hunan 410003, China
  • Received:2011-09-23 Revised:2011-10-10 Online:2012-03-01 Published:2012-03-01
  • Contact: Yong-Xing HE

摘要: 针对大规模散乱点云的配准,提出一种基于邻域特征的配准方法,该方法由初始配准和精确配准组成。首先,对目标点集进行加权处理,以此来有效减少匹配点对的数量;其次,在重心距离特征的基础上,增加了一个角度特征量来排除错误点对,并完成初始配准;最后,使用特征改进的迭代最近点(ICP)算法进行精确配准。实验结果表明,该方法初始配准结果良好,二次配准效果更加准确,达到了多视角点云的配准要求。

关键词: 点云, 初始配准, 精确配准, 邻域特征, 迭代最近点算法

Abstract: A new registration method of large-scale scattered point clouds based on invariant features of neighborhood was proposed, which consisted of preliminary registration and exact registration. Firstly, the target point set was weighted to reduce the amount of corresponding point-pairs efficiently. Secondly, on the basis of distance features between points and their neighborhood centroids, this paper added an additional geometric feature vector of included angle to eliminate bad point-pairs, and then the preliminary registration was completed. Finally, the Iterative Closest Point (ICP) algorithm with improved invariant feature was used to register accurately. The experimental results indicate the good results of the preliminary registration and the better results of the exact registration, which have met the requirement of registering point clouds from different viewpoints.

Key words: point cloud, preliminary registration, exact registration, neighborhood feature, Iterative Closest Point (ICP) algorithm

中图分类号: