基于曲率的点云自动配准方法

系统仿真学报 ›› 2015, Vol. 27 ›› Issue (10): 2374-2379.

基于曲率的点云自动配准方法

余文利^1,2, 周明全^1,2, 税午阳^1,2, 武仲科^1,2

1.北京师范大学信息科学与技术学院,北京 100875;
2.教育部虚拟现实应用工程中心,北京 100875

收稿日期:2015-06-14 修回日期:2015-07-24 出版日期:2015-10-08 发布日期:2020-08-07
作者简介:余文利(1991-),女,陕西,硕士生,研究方向虚拟现实与可视化技术。
基金资助:
国家自然科学基金(61202198, 61402042); 中央高校基本科研业务费(2013YB70, 2013YB72); 国家科技支撑计划(2012BAH33F04)

Automatic Registration Method Based on Curvature

Yu Wenli^1,2, Zhou Mingquan^1,2, Shui Wuyang^1,2, Wu Zhongke^1,2

1. Department of Information Technology, Beijing Normal University, Beijing 100875, China;
2. Engineering Research Center for Virtual Reality Applications, MOE, Beijing 100875, China

Received:2015-06-14 Revised:2015-07-24 Online:2015-10-08 Published:2020-08-07

摘要/Abstract

摘要： 由于三维扫描仪采集范围的制约,单次扫描仅得到单一视角的深度图像,需研究深度图像的配准问题实现三维建模。现有商业软件大多需要人工标定实现深度图像配准,为改进此问题,提出一种基于曲率约束的三维点云自动配准法。采用4PCS方法实现两个三维点云模型的自动初配准,用点到面的ICP法及最小二乘法,计算三维模型的刚性变换矩阵。为消除迭代过程中的误匹配,将顶点曲率作为约束,提高了点云配准的准确性。实验结果表明：根据曲率约束去除错误匹配点对后,配准精度提高。

关键词: ICP, 点云配准, 曲率, 点到面ICP, 点到点ICP

Abstract: Due to the acquisition range constriction of three-dimensional, a scanner could only obtain a single perspective of the deep image achieving the 3-D modeling from researching the registration of deep image. Currently, most of the existing commercial software requires manual label to achieve the registration of deep image. In order to improve this problem, an automatic registration method based on the constriction of curvature was proposed. At the beginning of registration, the method 4-Points Congruent Sets for Robust Surface Registration (4PCS) was used to achieve the initial and automatic registration. In the phase of accurate registration, ICP and linear least-square optimization method was used to get 3-D model's Rigid transformation matrix. In order to eliminate the iterative process of mismatch problem, the curvature as a constraint was taken to improve the accuracy of point cloud registration. Experiment indicates that after the removal of false match points according to the constraint of curvature, the registration accuracy of the model is increased and perfect.

Key words: ICP, cloud registration, curvature, point-to-plane ICP, point-to-point ICP

中图分类号:

TP391.9

余文利, 周明全, 税午阳, 武仲科. 基于曲率的点云自动配准方法[J]. 系统仿真学报, 2015, 27(10): 2374-2379.

Yu Wenli, Zhou Mingquan, Shui Wuyang, Wu Zhongke. Automatic Registration Method Based on Curvature[J]. Journal of System Simulation, 2015, 27(10): 2374-2379.

参考文献

[1] Frome A, Huber D, Kolluri R, et al. Recognizing objects in range data using regional point descriptors[M]// Computer Vision-ECCV 2004. Germany: Springer Berlin Heidelberg, 2004: 224-237.
[2] Aiger D, Mitra N J. Cohen-Or D.4-points congruent sets for robust pairwise surface registration[C]// ACM Transactions on Graphics (TOG). USA: ACM, 2008, 27(3): 85.
[3] Besl P J, McKay N D. A Method for registration of 3-D shapes[C]// Robotics-DL tentative. USA: International Society for Optics and Photonics, IEEE Computer Society, 1992: 586-606.
[4] Kung S Y, Arun K S, Rao D V.State-space and singular-value decomposition-based approximation methods for the harmonic retrieval problem[J]. JOSA (S1799-1811), 73(12): 1983.
[5] Low K L.Linear least-squares optimization for point-to-plane icp surface registration[M]. Chapel Hill, USA: University of North Carolina, 2004.
[6] Blais G, Levine M D.Registering multiview range data to create 3D computer objects[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1995, 17(8): 820-824.
[7] Okatani I S, Deguchi K.A method for fine registration of multiple view range images considering the measurement error properties[C]// Pattern Recognition, 2000, Proceedings, 15th International Conference on. USA: IEEE, 2000, 1: 280-283.
[8] Rusinkiewicz S, Levoy M.Efficient variants of the ICP algorithm[C]// 3-D Digital Imaging and Modeling, 2001. Proceedings, Third International Conference on. USA: IEEE, 2001: 145-152.
[9] Agarwal P K, Sharir M.The number of congruent simplices in a point set[J]. Discrete and Computational Geometry (S1432-0444), 2002, 28(2): 123-150.
[10] Fischler M A, Bolles R C.Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography[J]. Communications of the ACM, 1981, 24(6): 726-740.
[11] Callieri M, Fasano A, Impoco G, et al. RoboScan: an automatic system for accurate and unattended 3D scanning[C]// 3D Data Processing, Visualization and Transmission, 2004, 3DPVT 2004, Proceedings, 2nd International Symposium on. USA: IEEE, 2004: 805-812.
[12] Chen Y, Medioni G.Object modeling by registration of multiple range images[C]// Robotics and Automation, 1991, Proceedings 1991 IEEE International Conference on. USA: IEEE, 1991: 2724-2729.
[13] Chen C S, Hung Y P, Cheng J B.RANSAC-based DARCES: A new approach to fast automatic registration of partially overlapping range images[C]// Pattern Analysis and Machine Intelligence, IEEE Transactions on Pami21.11. USA: IEEE, 1999: 1229-1234.
[14] Arun K S, Huang T S, Blostein S D.Least-Squares Fitting of Two 3-D Point Sets[J]. IEEE Trans. Pattern Anal. Mach. Intell., 1987, 9(5): 698-700.
[15] Liu Yuncai, T S Huang. Estimation of rigid body motion using straight line correspondences[J]. Computer Vision Graphics & Image Processing, 1988, 43(88): 37-52.
[16] Horn B K P. Closed-form solution of absolute orientation using unit quaternions[J]. JOSA A, 1987, 4(4): 629-642.
[17] Pottmann Helmut, S Leopoldseder, M Hofer. Registration without ICP[J]. Computer Vision & Image Understanding, 2004, 95(1): 54-71.