基于点到面度量的多视角点云配准方法

马洁莹; 田暄; 翟庆; 王丞

doi:10.7652/xjtuxb202206015

您当前的位置：

首页 >

文章列表页 >

基于点到面度量的多视角点云配准方法

—————————————————————— | 更新时间：2025-04-27

- 基于点到面度量的多视角点云配准方法
- Registration of Multi-View Point Sets Based on Point-to-Plane Measurement
- 西安交通大学学报 2022年56卷第6期页码：120-132
- 作者机构：
  
  西安交通大学软件学院,西安,710049
- 作者简介：
  
  : 2021-11-18。作者简介: 马洁莹(1998—),女,硕士生
  田暄(通信作者),男,讲师。基金项目: 陕西省重点研发计划项目(2021GY-025)
- 基金信息：
  
  : 2021-11-18。作者简介: 马洁莹(1998—),女,硕士生;田暄(通信作者),男,讲师。基金项目: 陕西省重点研发计划项目(2021GY-025)
- DOI：10.7652/xjtuxb202206015
  中图分类号： TP391
- 网络首发：2022-06-10，
  
  纸质出版：2022
- 稿件说明：
移动端阅览
马洁莹, 田暄, 翟庆, 等. 基于点到面度量的多视角点云配准方法[J]. 西安交通大学学报, 2022,56(6):120-132.

MA Jieying, TIAN Xuan, ZHAI Qing, et al. Registration of Multi-View Point Sets Based on Point-to-Plane Measurement[J]. 2022, 56(6): 120-132.
马洁莹, 田暄, 翟庆, 等. 基于点到面度量的多视角点云配准方法[J]. 西安交通大学学报, 2022,56(6):120-132. DOI： 10.7652/xjtuxb202206015.

MA Jieying, TIAN Xuan, ZHAI Qing, et al. Registration of Multi-View Point Sets Based on Point-to-Plane Measurement[J]. 2022, 56(6): 120-132. DOI： 10.7652/xjtuxb202206015.

摘要

针对现有的大多数基于点到点度量的多视角点云配准方法在配准过程中

由于物体表面离散化而无法获得点到点的精确重叠

从而导致的收敛速度慢、配准精度低的问题

提出一种基于点到面度量的多视角点云配准方法。为获得多视角点云匹配结果

采用逐步求精的策略将多视角配准问题分解成多个点到面双视角配准子问题进行求解。在双视角配准过程中:使用数据点与对应点处切平面的距离误差代替点对距离误差

给出新的目标函数; 提出高效法向量转换策略

以减少多视角配准的每次迭代中平面法向量的求解次数。在目标函数的求解过程中

用线性最小二乘法逼近非线性优化问题

从而实现点到平面误差的最小化。将所提方法在斯坦福数据集上进行了测试

实验结果表明:与当下较为流行的多视角配准方法相比

所提方法在不同数据集上的旋转误差均降低了38.9%以上

平移误差均降低了16.6%以上

能够快速实现精确、可靠的多视角点云配准。

Abstract

Most of the existing multi-view point set registration methods based on point-to-point measurement cannot obtain the accurate overlap of the individual points due to the discretization of object surface

resulting in the problems of slow convergence and low registration accuracy. To solve this problem

this paper proposed a multi-view point set registration method based on point-to-plane measurement. To achieve the multi-view registration

the proposed method uses the stepwise refinement strategy to break down the multi-view registration problem into several point-to-plane pair-wise registration problems. In the pair-wise registration process

first of all

a new objective function is given which uses the point-to-plane error to replace the point-to-point distance error; Secondly

an effective normal vector transformation strategy is proposed to reduce the times of solving the plane normal vector in each iteration of the multi-view point set registration. Then

in the process of solving the objective function

the linear least square method is used to approximate the nonlinear optimization problem

so as to minimize the point-to-plane error. Finally

the proposed method is tested on Stanford data sets

and the experimental results show that: compared with four other multi-view registration methods

the proposed method reduces the rotation error by more than 38.9% in terms of different data sets

and the translation error by more than 16.6%

thus effectively achieving accurate and reliable multi-view point sets registration.

关键词

Keywords

references

SUN Jing, SUN Zhanli, LAM K M, et al. A robust point set registration approach with multiple effective constraints [J]. IEEE Transactions on Industrial Electronics, 2020, 67(12): 10931-10941.

林伟, 孙殿柱, 李延瑞, 等. 形貌约束的多视角点云分阶配准方法 [J]. 西安交通大学学报, 2020, 54(6): 75-81.

LIN Wei, SUN Dianzhu, LI Yanrui, et al. A hierarchical registration method of multiview point clouds with shape constraints [J]. Journal of Xi'an Jiaotong University, 2020, 54(6): 75-81.

PAVAN N L, DOS SANTOS D R, KHOSHELHAM K. Global registration of terrestrial laser scanner point clouds using plane-to-plane correspondences [J]. Remote Sensing, 2020, 12(7): 1127.

FANG Bin, MA Jie, AN Pei, et al. Multi-level height maps-based registration method for sparse LiDAR point clouds in an urban scene [J]. Applied Optics, 2021, 60(14): 4154-4164.

LIN Zhiyang, ZHU Jihua, JIANG Zutao, et al. Merging grid maps in diverse resolutions by the context-based descriptor [J]. ACM Transactions on Internet Technology, 2021, 21(4): 91.

陆世东, 涂美义, 罗小勇, 等. 基于图优化理论和GNSS激光SLAM位姿优化算法 [J]. 激光与光电子学进展, 2020, 57(8): 208-217.

LU Shidong, TU Meiyi, LUO Xiaoyong, et al. Laser SLAM pose optimization algorithm based on graph optimization theory and GNSS [J]. Laser Optoelectronics Progress, 2020, 57(8): 208-217.

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.

CHETVERIKOV D, SVIRKO D, STEPANOV D, et al. The trimmed iterative closest point algorithm [C]∥2002 International Conference on Pattern Recognition. Piscataway, NJ, USA: IEEE, 2002: 545-548.

MAGNUSSON M, LILIENTHAL A, DUCKETT T. Scan registration for autonomous mining vehicles using 3D-NDT [J]. Journal of Field Robotics, 2007, 24(10): 803-827.

BOUAZIZ S, TAGLIASACCHI A, PAULY M. Sparse iterative closest point [J]. Computer Graphics Forum, 2013, 32(5): 113-123.

SHI Xiaojing, LIU Tao, HAN Xie. Improved iterative closest point(ICP)3D point cloud registration algorithm based on point cloud filtering and adaptive fireworks for coarse registration [J]. International Journal of Remote Sensing, 2020, 41(8): 3197-3220.

沈江华, 孙殿柱, 李延瑞, 等. 点云初始配准的优化求解算法 [J]. 西安交通大学学报, 2019, 53(8): 167-174.

SHEN Jianghua, SUN Dianzhu, LI Yanrui, et al. An optimization algorithm for initial registration of point clouds [J]. Journal of Xi'an Jiaotong University, 2019, 53(8): 167-174.

彭真, 吕远健, 渠超, 等. 基于关键点提取与优化迭代最近点的点云配准 [J]. 激光与光电子学进展, 2020, 57(6): 60-71.

PENG Zhen, LV Yuanjian, QU Chao, et al. Accurate registration of 3D point clouds based on keypoint extraction and improved iterative closest point algorithm [J]. Laser Optoelectronics Progress, 2020, 57(6): 60-71.

PAVLOV A L, OVCHINNIKOV G W, DERBYSHEV D Y, et al. AA-ICP: iterative closest point with Anderson acceleration [C]∥2018 IEEE International Conference on Robotics and Automation(ICRA). Piscataway, NJ, USA: IEEE, 2018: 3407-3412.

ZHANG Juyong, YAO Yuxin, DENG Bailin. Fast and robust iterative closest point [J/OL]. IEEE transactions on Pattern Analysis and Machine Intelligence, 2021[2021-10-01]. https:∥doi.org/10.1109/tpami.2021.3054619.

CHEN Yang, MEDIONI G. Object modelling by registration of multiple range images [J]. Image and Vision Computing, 1992, 10(3): 145-155.

RUSINKIEWICZ S, LEVOY M. Efficient variants of the ICP algorithm [C]∥Proceedings of the Third International Conference on 3-D Digital Imaging and Modeling. Piscataway, NJ, USA: IEEE, 2001: 145-152.

LOW K L. Linear least-squares optimization for point-to-plane ICP surface registration: TR04-004 [R]. Raleigh, NC, USA: University of North Carolina at Chapel Hill, 2004.

PARK J, ZHOU Qianyi, KOLTUN V. Colored point cloud registration revisited [C]∥2017 IEEE International Conference on Computer Vision(ICCV). Piscataway, NJ, USA: IEEE, 2017: 143-152.

RUSINKIEWICZ S. A symmetric objective function for ICP [J]. ACM Transactions on Graphics, 2019, 38(4): 85.

BERGEVIN R, SOUCY M, GAGNON H, et al. Towards a general multi-view registration technique [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1996, 18(5): 540-547.

徐思雨, 祝继华, 田智强, 等. 逐步求精的多视角点云配准方法 [J]. 自动化学报, 2019, 45(8): 1486-1494.

XU Siyu, ZHU Jihua, TIAN Zhiqiang, et al. Stepwise refinement approach for registration of multi-view point sets [J]. Acta Automatica Sinica, 2019, 45(8): 1486-1494.

GOJCIC Z, ZHOU Caifa, WEGNER J D, et al. Learning multiview 3D point cloud registration [C]∥2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Piscataway, NJ, USA: IEEE, 2020: 1756-1766.

ZHU Jihua, JIANG Zutao, EVANGELIDIS G D, et al. Efficient registration of multi-view point sets by K-means clustering [J]. Information Sciences, 2019, 488: 205-218.

MATEO X, ORRIOLS X, BINEFA X. Bayesian perspective for the registration of multiple 3D views [J]. Computer Vision and Image Understanding, 2014, 118: 84-96.

ZHU Jihua, GUO Rui, LI Zhongyu, et al. Registration of multi-view point sets under the perspective of expectation-maximization [J]. IEEE Transactions on Image Processing, 2020, 29: 9176-9189.

林桂潮, 唐昀超, 邹湘军, 等. 融合高斯混合模型和点到面距离的点云配准 [J]. 计算机辅助设计与图形学学报, 2018, 30(4): 642-650.

LIN Guichao, TANG Yunchao, ZOU Xiangjun, et al. Point cloud registration algorithm combined Gaussian mixture model and point-to-plane metric [J]. Journal of Computer-Aided Design Computer Graphics, 2018, 30(4): 642-650.

CHAMROUKHI F. Robust mixture of experts modeling using the t distribution [J]. Neural Networks, 2016, 79: 20-36.

RAVIKUMAR N, GOOYA A, ÇIMEN S, et al. Group-wise similarity registration of point sets using student's t-mixture model for statistical shape models [J]. Medical Image Analysis, 2018, 44: 156-176.

GOVINDU V M, POOJA A. On averaging multiview relations for 3D scan registration [J]. IEEE transactions on Image Processing, 2014, 23(3): 1289-1302.

ARRIGONI F, ROSSI B, FUSIELLO A. Global registration of 3D point sets via LRS decomposition [C]∥Proceedings of the 2016 European Conference on Computer Vision(ECCV). Cham, Germany: Springer International Publishing, 2016: 489-504.

ZHANG Xin, ZHANG Yan, QU Chengzhi, et al. Fast and robust motion averaging via angle constraints of multi-view range scans [J]. The Journal of Engineering, 2021(2): 104-113.

NUCHTER A, LINGEMANN K, HERTZBERG J. Cached k-d tree search for ICP algorithms [C]∥Sixth International Conference on 3-D Digital Imaging and Modeling(3DIM 2007). Piscataway, NJ, USA: IEEE, 2007: 419-426.

Standford University. The Stanford 3D scanning repository [EB/OL].(2014-08-19)[2021-10-01]. https:∥graphics.stanford.edu/data/3Dscanrep/.

EVANGELIDIS G D, HORAUD R. Joint alignment of multiple point sets with batch and incremental expectation-maximization [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40(6): 1397-1410.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

无序多视角点云的自主配准方法

融合物理信息与深度算子网络的变压器绕组热-流场快速计算方法

水蒸气掺混对氨裂解气旋流燃烧与排放特性的影响研究

电动车辆间接热系统快速除湿响应迟滞机理及优化控制策略

电子级超纯氮深冷空分流程节能优化研究