Point cloud registration based on improved iterative closest point method

WANG Xin; ZHANG Ming-ming; YU Xiao; ZHANG Ming-chao

doi:10.3788/OPE.20122009.2068

您当前的位置：

首页 >

文章列表页 >

Point cloud registration based on improved iterative closest point method

Article | 更新时间：2020-08-12

- Point cloud registration based on improved iterative closest point method
- Optics and Precision Engineering Vol. 20, Issue 9, Pages: 2068-2077(2012)
- 作者机构：
  
  1. 中国科学院长春光学精密机械与物理研究所应用光学国家重点实验室,吉林长春,130033
  2. 吉林大学计算机科学与技术学院,吉林长春,130012
  3. 空军航空大学训练部,吉林长春,130022
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20122009.2068
  CLC： TP391.41
- Received：17 April 2012，
  
  Revised：23 May 2012，
  
  Published：10 September 2012
- 稿件说明：
移动端阅览
王欣, 张明明, 于晓, 章明朝. 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 Xin, ZHANG Ming-ming, YU Xiao, ZHANG Ming-chao. Point cloud registration based on improved iterative closest point method[J]. Editorial Office of Optics and Precision Engineering, 2012,20(9): 2068-2077
王欣, 张明明, 于晓, 章明朝. 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 DOI： 10.3788/OPE.20122009.2068.

WANG Xin, ZHANG Ming-ming, YU Xiao, ZHANG Ming-chao. Point cloud registration based on improved iterative closest point method[J]. Editorial Office of Optics and Precision Engineering, 2012,20(9): 2068-2077 DOI： 10.3788/OPE.20122009.2068.

摘要

提出了基于点云边界特征点的改进迭代最近点(ICP)方法来提高逆向工程中点云数据配准的效率和精度。首先

提出了基于点云边界特征点的初始配准方法。对点云最小包围盒进行三维空间划分

建立空间网格模型;运用边界种子网格识别及生长算法

从点云边界提取特征点

运用奇异值矩阵分解法(SVD)求出点云的变换矩阵

得到初始配准结果。然后

提出了改进的ICP精确配准方法。对点云对应点赋予权重

剔除权重大于阈值的点

通过对目标函数引入M-估计(M-estimation)

剔除异常点。最后

在初始配准的基础上

运用改进的ICP方法精确配准。对经典ICP方法和改进ICP方法做对比实验

结果显示

改进方法的配准效率提高了70%以上

误差减小到0.02%。实验表明

本文方法大幅提高了点云配准的效率和精度。

Abstract

An improved Iterative Closest Point (ICP) method based on the boundary feature points of the point cloud is proposed to improve the efficiency and accuracy of point cloud data registration in reverse engineering fields. First

an initial registration method based on the boundary feature points of point cloud is proposed. The method partitions the minimum bounding box of point cloud with grids in a 3D space

and sets up the space grid model. Then

it applies boundary seed grid recognition and growth algorithms to extract feature points from the boundary of point cloud

and works out the transformation matrix using Singular Value Decomposition (SVD) method to get the results of initial registration. Furthermore

an improved ICP accurate registration method is presented. It weighs the corresponding points of the point cloud

eliminates the points whose weight is larger than the threshold

and introduces M-estimation to the objective function to eliminate the abnormal points. Finally

the point cloud is accurately registered by the improved ICP method on the basis of initial registration. Compared with original ICP method

the improved ICP method increases the efficiency by more than 70 percent and reduces the error to 0.02 percent. The experiment results indicate that the method proposed in this paper improves the efficiency and accuracy of point cloud registration greatly.

关键词

Keywords

references

DUN W Z, HUN G, HONG L X, et al.. The research of optical 3D measuring precision influencing factor in reverse engineering [J]. Applied Mechanics and Materials, 2010, 33: 157-162.[2] 孟凡文, 吴禄慎. 用继承与优化算法精密拼接无序点云[J]. 光学精密工程, 2009, 17(4): 825-831. MENG F W, WU L S. Registration of unorganized point clouds by inheriting and optimizing algorithm [J]. Opt. Precision Eng., 2009, 17(4): 825-831. (in Chinese)[3] 田庆国, 葛宝臻, 杜朴, 等. 基于激光三维扫描的人体特征尺寸测量[J]. 光学精密工程, 2007, 15(1): 84-88. TIAN Q G, GE B Z, DU P, et al.. Measurment of human figure size based on laser 3D scanning [J]. Opt. Precision Eng., 2007, 15(1): 84-88. (in Chinese)[4] HACENE A, MEKKI A. Bio-CAD reverse engineering of free-form surfaces by planar contours [J], Computer-Aided Design & Applications, 2011, 8(1): 37-42.[5] 龚卫国, 张旋, 李正浩. 基于局部敏感散列算法的图像配准 [J]. 光学精密工程, 2011, 19(6): 1375-1383. GONG W H, ZHANG X, LI Z H. Image registration based on extended LSH [J]. Opt. Precision Eng., 2011, 19(6): 1375-1383. (in Chinese)[6] 刘向增, 田铮, 史振广, 等. 基于FKICA-SIFT特征的合成孔径图像多尺度配准 [J]. 光学精密工程, 2011, 19(9): 2186-2196. LIU X Z, TIAN Z, SHI Z G, et al.. SAR image multi-scale registration based on FKICA-SIFT features [J]. Opt. Precision Eng., 2011, 19(9): 2186-2196. (in Chinese)[7] BESL P J, MCKAY N D. A method for registration of 3-D shapes [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1992, 14(2): 239-256.[8] DU S Y, ZHENG N N, YING S H, et al.. Affine iterative closest point algorithm for point set registration [J]. Pattern Recognition Letters, 2010, 31(9): 791-799.[9] ZHU J H, ZHENG N N, YUAN Z J. Robust scaling iterative closest point algorithm with bidirectional distance measurement [J]. Electronics Letters, 2010, 46(24): 1604-1605.[10] GREG T, MARC L. Zippered polygon meshes from range images. Proceedings of SIGGRAPH, 1994: 311-318.[11] MASUDA T, SAKAUE K, YOKOYA N. Registration and integration of multiple range images for 3-D model construction. Proceedings of the 13th International Conference on Pattern Recognition, 1996: 879-883.[12] RUSINKIEWICZ S, LEVOY M. Efficient variants of the ICP algorithm. Third International Conference on 3-D Digital Imaging and Modeling, 2001: 145-152.[13] CHEN Y, MEDIONI G. Object modeling by registration of multiple range images. Proceedings of IEEE International Conference on Robotics and Automation, 1991: 2724-2729.[14] JOST T. Fast Geometric matching for shape registration. Neuchatel, Switzerland: University of Neuchatel, 2002.[15] 柯映林, 范树迁. 基于点云的边界特征直接提取技术 [J]. 机械工程学报, 2004, 40(9): 116-120. KE Y L, FAN S Q. Research on direct extraction of boundary from point clouds [J]. Chinese Journal of Mechanical Engineering, 2004, 40(9): 116-120. (in Chinese)[16] LAURA E W, JOHN F P. A bounding box search algorithm for DEM simulation [J]. Computer Physics Communications, 2011, 182(2): 281-288.[17] STEFAN G, XINLONG W, ROB M. Feature extraction from point clouds. 10th International Meshing Roundtable, Sandia National Laboratories, 2001: 293-305.[18] 李敏. 基于多尺度特征提取的3D点云匹配的4PCS算法. 长春:吉林大学, 2010. LI M. 4 points fast matching algorithm for 3D data based on multi-scale feature exaction . Changchun:Jilin University, 2010. (in Chinese)[19] LAMBERT M S, MIRIAM T T, SUSAN F M. Singular Value Decomposition [M]. VDM Verlag Dr. Mueller e.K, 2010.[20] PETER J H. Robust statistics [M]. New York: John Wiley & Sons, Inc, 2005.[21] AIGER D, MITRA N J, COHEN-OR D. 4-points congruent sets for robust surface registration [J]. ACM Trans. Graph. (Proc. SIGG PH 2008), 2008,27(3):1-10.

Views

235

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

Fast registration of point cloud of complex hollow turbine blade

Registration of heterogeneous point cloud and precise reconstruction of 3D terrain via complex slope surface fitting

Design of partial overlap point cloud registration network driven by overlap score and matching matrix

Visual 6D pose estimation of battery package locking mechanism in intelligent battery swapping station

Related Author

Sen LIN

Qiang ZHANG

CAI Yong

GOU Chen

LIAO Xiaobo

LI Tong

ZHOU Xin

ZHUANG Jian

Related Institution

College of Electronic and Information Engineering，Liaoning Technology University

College of Automation and Electrical Engineering， Shenyang Ligong University

Sichuan Electronic and Mechanic Vocational College

School of Mechanical Engineering， Xi'an Jiaotong University

School of Manufacturing Science and Engineering， Southwest University of Science and Technology

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