Registration of losing point cloud based on clustering extended Gaussian image

WU Qing-hua; CAI Qiong-jie-si; LI Zhi-ang; LIU Jia-cheng

doi:10.37188/OPE.20212905.1199

您当前的位置：

首页 >

文章列表页 >

Registration of losing point cloud based on clustering extended Gaussian image

Information Sciences | 更新时间：2026-09-11

- Registration of losing point cloud based on clustering extended Gaussian image
- Optics and Precision Engineering Vol. 29, Issue 5, Pages: 1199-1206(2021)
- 作者机构：
  
  1.湖北省现代制造质量工程重点实验室，湖北武汉 430064
  2.湖北工业大学机械工程学院，湖北武汉 430064
- 作者简介：
- 基金信息：
- DOI：10.37188/OPE.20212905.1199
  CLC： TP242
- Received：16 December 2020，
  
  Revised：2021-01-07，
  
  Published：15 May 2021
- 稿件说明：
移动端阅览
吴庆华,蔡琼捷思,黎志昂等.扩展高斯图像聚类的缺失点云配准[J].光学精密工程,2021,29(05):1199-1206.

WU Qing-hua,CAI Qiong-jie-si,LI Zhi-ang,et al.Registration of losing point cloud based on clustering extended Gaussian image[J].Optics and Precision Engineering,2021,29(05):1199-1206.
吴庆华,蔡琼捷思,黎志昂等.扩展高斯图像聚类的缺失点云配准[J].光学精密工程,2021,29(05):1199-1206. DOI： 10.37188/OPE.20212905.1199.

WU Qing-hua,CAI Qiong-jie-si,LI Zhi-ang,et al.Registration of losing point cloud based on clustering extended Gaussian image[J].Optics and Precision Engineering,2021,29(05):1199-1206. DOI： 10.37188/OPE.20212905.1199.

摘要

针对局部缺失点云配准时精度不高和收敛过慢等问题，提出了一种基于扩展高斯图像聚类的快速点云配准算法。通过将点云映射到扩展高斯图像中进行聚类后逆映射实际点云获取待配准的子点云，进而规避局部缺失带来的干扰；此外，为提高计算效率和配准精度，采用距离-曲率描述子查询对应点对进行奇异值分解进行粗配准，并结合迭代最近点精配准算法实现点云配准过程。实验结果表明，该算法对于局部缺失点云具有较高精度（均方误差相对于结合ICP的传统算子FPFH降低了近17.9%），且相比其它算法有一定的速度优势（耗时相对于结合ICP的SHOT算子加速了近32.5%）。该算法可以有效的运用在局部缺失点云的位姿识别中，从而可以被广泛地应用于工业现场中三维物体的快速识别定位。

Abstract

With the aim of tackling the registration problems in terms of low matching accuracy and low convergence speed in locally losing point clouds， a fast point cloud registration algorithm based on a clustering extended Gaussian image is proposed herein. To avoid the interference due to local loss， the point cloud is mapped to the extended Gaussian image for clustering and inversely mapped back to the actual point cloud. Moreover， to improve the efficiency of computation and the accuracy of registration， the process of point cloud registration is realized by using the distance–curvature descriptor to obtain the corresponding point pairs and the iterative closest point （ICP） algorithm. The experimental results reveal that this algorithm displays high accuracy in the case of locally losing point clouds （resulting in a mean squared error （MSE） value lowered by 17.9% for the fast point feature histogram （FPFH） descriptor combined with the ICP algorithm）. Moreover， it is faster than other algorithms （resulting in a decrease in running time by 32.5% for the signature of histograms of orientation （SHOT） descriptor combined with the ICP algorithm）. Therefore， it can be widely applied for fast recognition and location of three-dimensional objects in the industrial field.

关键词

Keywords

references

宗文鹏，李广云，李明磊，等 . 激光扫描匹配方法研究综述［J］. 中国光学， 2018 ， 11 （ 6 ）： 914 - 930 .

ZONG W P ， LI G Y ， LI M L ， et al . A survey of laser scan matching methods ［J］. Chinese Optics ， 2018 ， 11 （ 6 ）： 914 - 930 . （in Chinese）

马扬飚，钟约先，郑聆，等 . 三维数据拼接中编码标志点的设计与检测［J］. 清华大学学报（自然科学版）， 2006 ，（ 2 ）： 169 - 171+175 .

MA Y B ， ZHONG Y X ， ZHEN L ， et al . Design and recognition of coded targets for 3-D registration ［J］. Journal of Tsinghua University（Science and Technology）， 2006 ，（ 2 ）： 169 - 171+175 . （in Chinese）

BESL P J . A method for registration of 3d shapes ［J］. IEEE Trans on PAMI ， 1992 ， 14 .

汤慧，周明全，耿国华 . 基于区域分割的低覆盖点云配准算法［J］. 计算机应用， 2019 ， 39 （ 11 ）： 3355 - 3360 .

TANG H ， ZHOU M Q ， GENG G H . Low coverage point cloud registration algorithm based on region segmentation ［J］. Journal of Computer Applications ， 2019 ， 39 （ 11 ）： 3355 - 3360 . （in Chinese）

RUSU R B ， BLODOW N ， BEETZ M . Fast Point Feature Histograms （FPFH） for 3D registration ［C］. IEEE International Conference on Robotics & Automation . IEEE ， 2009 .

SALTI S ， TOMBARI F ， STEFANO L D . SHOT： Unique signatures of histograms for surface and texture description ［J］. Computer Vision & Image Understanding ， 2014 ， 125 （ 8 ）： 251 - 264 .

王欣，张明明，于晓，等 . 应用改进迭代最近点方法的点云数据配准［J］. 光学精密工程， 2012 ， 20 （ 9 ）： 2068 - 2077 .

WANG X ， ZHANG M M ， YU X ， et al . Point cloud registration based on improved iterative closest point method ［J］. Opt. Precision Eng. ， 2012 ， 20 （ 9 ）： 2068 - 2077 . （in Chinese）

MAGNUSSON M ， ANDREASSON H ， NUCHTER A ， et al . Appearance-based loop detection from 3D laser data using the normal distributions transform ［C］. IEEE International Conference on Robotics & Automation . IEEE ， 2012 .

徐卫青，陈西江，章光，等 . 一种基于高斯映射的三维点云特征线提取方法［J］. 激光与光电子学进展， 2019 ， 56 （ 9 ）： 167 - 173 .

XU W Q ， CHEN X J ， ZHANG G ， et al . Method for extraction of feature lines of three-dimensiona laser point cloud based on Gaussian map ［J］. Laser & Optoelectronics Progress ， 2019 ， 56 （ 9 ）： 167 - 173 . （in Chinese）

IVÁN D . GARCÍA-SANTILLÁN， GONZALO P. On-line crop/weed discrimination through the Mahalanobis distance from images in maize fields ［J］. Biosystems Engineering ， 2017 ， 166 ： 28 - 43 .

PATTERSON A ， DANIILIDIS K ， MAKADIA A . Fully automatic registration of 3d point clouds ［C］. IEEE Computer Society Conference on Computer Vision & Pattern Recognition. IEEE Computer Society ， 2013 .

LI F ， STODDART D ， HITCHENS C . Method to automatically register scattered point clouds based on principal pose estimation ［J］. Optical Engineering ， 2017 ， 56 （ 4 ）.

ZHANG X P ， LI H J ， CHENG Z L . Curvature estimation of 3D point cloud surfaces through the fitting of normal section curvatures ［C］. Proceedings of ASIAGRAPH ， 2008 ，（ 2008 ）： 23 - 26 .

FISCHLER M A ， BOLLES R C . Random sample consensus： A paradigm for model fitting with applications to image analysis and automated cartography ［J］. Readings in Computer Vision ， 1987 ： 726 - 740 .

VINCENT ， GUILLEMOT ， DEREK ， et al . A constrained singular value decomposition method that integrates sparsity and orthogonality ［J］. Plos One ， 2019 .

Views

736

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Point cloud registration using neighborhood point information description and matching

Point cloud registration by fusing deep feature consistency with attention network

Unsupervised point cloud registration algorithm integrating feature interaction and point matching enhancement

Point cloud registration using adaptive sampling and geometric-spatial feature fusion

Optimization design of combined brightfield and darkfield illumination system for machine vision measurement

Related Author

Sen LIN

Qiang ZHANG

ZHAO Fuqun

CHEN Junxi

ZHOU Mingquan

YI Jianbing

XIONG Wenwu

PENG Xin

Related Institution

College of Automation and Electrical Engineering， Shenyang Ligong University

College of Electronic and Information Engineering，Liaoning Technology University

School of Information， Xi'an University of Finance and Economics

Shaanxi Province Key Laboratory of Intelligent Finance Collaboration and Trusted Computing （Xi'an University of Finance and Economics）

School of Computer （School of Software）， Northwest University

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰