首页 > 论文 > 光学学报 > 39卷 > 1期(pp:115005--1)

基于多维混合柯西分布的点云配准

Point Cloud Registration Based on Multi-Dimensional Mixed Cauchy Distribution

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

为提高三维点云在数据随机缺失和噪声干扰等复杂情况下的配准精度, 提出一种基于多维混合柯西分布(MMC)的点云配准方法。将点云数学模型扩展为MMC模型, 求解模型各参数, 并构造出特征四面体,以优化旋转矩阵与平移向量; 通过最大期望算法分别求出目标点云和待配准点云在MMC模型下的数据中心、协方差矩阵和权重的值。仿真与实验数据表明:与几种常用的算法相比, MMC算法即使在点云数据存在遮挡、缺失, 大小不一致, 含随机噪声, 且具有无序性的条件下, 也能精确配准, 且具有良好的稳健性。

Abstract

To improve the registration accuracy of three-dimensional point clouds in the complex situations of random data missing, noise interference and so on, a method of registering point clouds based on multi-dimensional mixed Cauchy distribution (MMC) is proposed. The mathematical model of point clouds is extended to the MMC model, and the parameters of this model are solved to construct a characteristic tetrahedron so that the rotation matrix and translation vector are optimized. Based on the MMC model, the data centers, covariance matrices and weights of target point clouds and point clouds to register are obtained by the expectation-maximization algorithm. The simulation data and experimental data show that the MMC algorithm can be used to realize an accurate registration and simultaneously possesses a good robustness if compared with several common algorithms under the conditions that the point cloud data are occluded, missing, size-inconsistent, interfered by random noise and out of order.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP391.9

DOI:10.3788/aos201939.0115005

所属栏目:机器视觉

基金项目:国家自然科学基金(61802033)

收稿日期:2018-07-23

修改稿日期:2018-08-28

网络出版日期:2018-09-10

作者单位    点击查看

唐志荣:成都理工大学核技术与自动化工程学院, 四川 成都 610059
刘明哲:成都理工大学核技术与自动化工程学院, 四川 成都 610059成都理工大学地学核技术四川省重点实验室, 四川 成都 610059
王畅:四川大学电气信息学院, 四川 成都 610065
蒋悦:四川大学电气信息学院, 四川 成都 610065

联系人作者:刘明哲(liumz@cdut.edu.cn)

【1】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.

【2】Ying S H, Peng J G, Du S Y, et al. A scale stretch method based on ICP for 3D data registration[J]. IEEE Transactions on Automation Science and Engineering, 2009, 6(3): 559-565.

【3】Sharp G C, Lee S W, Wehe D K. ICP registration using invariant features[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(1): 90-102.

【4】Bae K H. Evaluation of the convergence region of an automated registration method for 3D laser scanner point clouds[J]. Sensors, 2009, 9(1): 355-375.

【5】Zeng F X, Li L, Diao X P. Iterative closest point algorithm registration based on curvature fatures[J]. Laser & Optoelectronics Progress, 2017, 54(1): 011003.
曾繁轩, 李亮, 刁鑫鹏. 基于曲率特征的迭代最近点算法配准研究[J]. 激光与光电子学进展, 2017, 54(1): 011003.

【6】Li Q S, Xiong R, Vidal-Calleja T. A GMM based uncertainty model for point clouds registration[J]. Robotics and Autonomous Systems, 2017, 91: 349-362.

【7】Jian B, Vemuri B C. Robust point set registration using Gaussian mixture models[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(8): 1633-1645.

【8】Myronenko A, Song X B. Point set registration: coherent point drift[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(12): 2262-2275.

【9】Zhang Z, Xu H L, Yin H. A fast point cloud registration algorithm based on key point selection[J]. Laser & Optoelectronics Progress, 2017, 54(12): 121001.
张哲, 许宏丽, 尹辉. 一种基于关键点选择的快速点云配准算法[J]. 激光与光电子学进展, 2017, 54(12): 121001.

【10】Prakhya S M, Liu B B, Lin W S, et al. B-SHOT: a binary 3D feature descriptor for fast keypoint matching on 3D point clouds[J]. Autonomous Robots, 2017, 41(7): 1501-1520.

【11】Ge X M. Automatic markerless registration of point clouds with semantic-keypoint-based 4-points congruent sets[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2017, 130: 344-357.

【12】Quan S W, Ma J, Hu F Y, et al. Local voxelized structure for 3D binary feature representation and robust registration of point clouds from low-cost sensors[J]. Information Sciences, 2018, 444: 153-171.

【13】Bae K H, Lichti D D. A method for automated registration of unorganised point clouds[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2008, 63(1): 36-54.

【14】Persad R A, Armenakis C. Automatic Co-registration of 3D multi-sensor point clouds[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2017, 130: 162-186.

【15】Bueno M, Gonzlez-Jorge H, Martínez-Snchez J, et al. Automatic point cloud coarse registration using geometric keypoint descriptors for indoor scenes[J]. Automation in Construction, 2017, 81: 134-148.

【16】Wang C, Shu Q, Yang Y X, et al. Quick registration algorithm of point clouds using structure feature[J]. Acta Optica Sinica, 2018, 38(9): 0911005.
王畅, 舒勤, 杨赟秀, 等. 利用结构特征的点云快速配准算法[J]. 光学学报, 2018, 38(9): 0911005.

【17】Ji S J, Ren Y C, Ji Z, et al. An improved method for registration of point cloud[J]. Optik-International Journal for Light and Electron Optics, 2017, 140: 451-458.

【18】Zhao M, Shu Q, Chen W, et al. 3D point cloud registration algorithm based on lp spatial mechanics model[J]. Acta Optica Sinica, 2018, 38(10): 1010005.
赵敏, 舒勤, 陈蔚, 等. 基于lp空间力学模型的三维点云配准算法[J]. 光学学报, 2018, 38(10): 1010005.

【19】Yang J L, Li H D, Campbell D, et al. Go-ICP: a globally optimal solution to 3D ICP point-set registration[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(11): 2241-2254.

【20】Campbell D, Petersson L. GOGMA: globally-optimal Gaussian mixture alignment[C]. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016: 5685-5694.

【21】Zeng A, Song S R, Niener M, et al. 3D Match: learning local geometric descriptors from RGB-D reconstructions[C]. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017: 199-208.

引用该论文

Tang Zhirong,Liu Mingzhe,Wang Chang,Jiang Yue. Point Cloud Registration Based on Multi-Dimensional Mixed Cauchy Distribution[J]. Acta Optica Sinica, 2019, 39(1): 0115005

唐志荣,刘明哲,王畅,蒋悦. 基于多维混合柯西分布的点云配准[J]. 光学学报, 2019, 39(1): 0115005

被引情况

【1】蒋悦,黄宏光,舒勤,宋昭,唐志荣. 高维正交子空间映射的尺度点云配准算法. 光学学报, 2019, 39(3): 315007--1

【2】唐志荣,刘明哲,蒋悦,赵飞翔,赵成强. 基于典型相关分析的点云配准算法. 中国激光, 2019, 46(4): 404006--1

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF