一种基于ISS-SHOT特征的点云配准算法

doi:10.13474/j.cnki.11-2246.2020.0106

测绘通报 ›› 2020, Vol. 0 ›› Issue (4): 21-26.doi: 10.13474/j.cnki.11-2246.2020.0106

一种基于ISS-SHOT特征的点云配准算法

李宇翔¹, 郭际明¹, 潘尚毅², 吕丽丽², 卢主兴¹, 章迪¹

1. 武汉大学测绘学院, 湖北武汉 430079;
2. 中国水利水电第四工程局有限公司, 青海西宁 810007

收稿日期:2019-07-01 修回日期:2020-03-02 出版日期:2020-04-25 发布日期:2020-05-08
通讯作者: 郭际明。E-mail:jmguo@sgg.whu.edu.cn E-mail:jmguo@sgg.whu.edu.cn
作者简介:李宇翔(1996-),男,硕士生,主要研究方向为点云数据处理。E-mail:lyx_whu@126.com
基金资助:
国家自然科学基金（41474004）；中国电力建设股份有限公司科研项目（KJ-2018-019）

A point cloud registration algorithm based on ISS-SHOT features

LI Yuxiang¹, GUO Jiming¹, PAN Shangyi², Lü Lili², LU Zhuxing¹, ZHANG Di¹

1. School of Geodesy and Geomatics, Wuhan University, Wuhan 430079, China;
2. Sinohydro Engineering Bureau;
4 Co., Ltd., Xining 810007, China

Received:2019-07-01 Revised:2020-03-02 Online:2020-04-25 Published:2020-05-08

摘要/Abstract

摘要： 针对点云配准过程中易产生错误对应点、收敛速度慢、配准时间长等问题，提出了一种基于内部形态描述子（ISS）及方向直方图描述子（SHOT）特征的点云配准算法。运用体素格网法下采样后，采用ISS算法提取特征点，并用SHOT对特征点进行描述，利用余弦相似度匹配对应点对，再采用RANSAC算法剔除错误对应点对，使得两片点云获得良好的初始位姿，最后采用点到平面的ICP算法进行精确配准。试验结果表明，与传统ICP算法及基于ISS的SAC-IA+ICP算法相比，本文算法配准精度及配准效率更高，对数据量大、重叠率较低点云具有很好的稳健性。

关键词: ISS, SHOT, 特征描述子, 点云配准, 点到平面ICP

Abstract: Aiming at the problems of error-corresponding points, slow convergence rate and long time for the point cloud registration, a registration algorithm based on theintrinsic shape signatures(ISS) and signature of histograms of orientations(SHOT) is proposed.After down-sampling by voxel grid method, the feature points of point cloud are extracted by the ISS algorithm, described by the SHOT and matched by the cosine similarity. Then, the wrong corresponding points are eliminated by the RANSAC algorithm, so that the two point clouds obtain a good initial positon. Finally, an accurate result can be obtained based on point to plane ICP algorithm.The experimental results show that compared with the traditional ICP algorithm and the ISS-based SAC-IA+ICP algorithm, the proposed algorithm has higher registration accuracy and efficiency, and it is robust to point clouds with large data quantity and low overlap rate.

Key words: ISS, SHOT, feature descriptor, point cloud registration, point to plane ICP

中图分类号:

P237

李宇翔, 郭际明, 潘尚毅, 吕丽丽, 卢主兴, 章迪. 一种基于ISS-SHOT特征的点云配准算法[J]. 测绘通报, 2020, 0(4): 21-26.

LI Yuxiang, GUO Jiming, PAN Shangyi, Lü Lili, LU Zhuxing, ZHANG Di. A point cloud registration algorithm based on ISS-SHOT features[J]. Bulletin of Surveying and Mapping, 2020, 0(4): 21-26.

参考文献

[1] 王延亮, 夏国芳, 胡春梅. 利用三维激光扫描技术进行工业设备三维重建及变形分析[J]. 测绘通报, 2012(2):94-96.
[2] 刘坤, 樊廷立, 杨晶, 等. 复杂环境下基于移动测量技术的城市数字地表数据的获取[J]. 测绘通报, 2017(6):165-166.
[3] 陈弘奕, 胡晓斌, 李崇瑞. 地面三维激光扫描技术在变形监测中的应用[J]. 测绘通报, 2014(12):74-77.
[4] BESL P J, MCKAY N D. A method for registration of 3-D shapes[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 1992, 14(2):239-256.
[5] CHEN Y, MEDIONI G G. Object modeling by registration of multiple range images[J]. Image and Vision Computing, 1992, 10(3):145-155.
[6] LI Q, GRIFFITHS J G. Iterative closest geometric objects registration[J]. Computers & Mathematics with Applications, 2000, 40(10):1171-1188.
[7] 刘斌, 郭际明, 邓祥祥. 结合八叉树和最近点迭代算法的点云配准[J]. 测绘科学, 2016, 41(2):130-132.
[8] JOHNSON A E, HEBERT M. Using spin images for efficient object recognition in cluttered 3D scenes[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2002, 21(5):433-449.
[9] RUSU R B, BLODOW N, MARTON Z C, et al. Aligning point cloud views using persistent feature histograms[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems.Nice:IEEE, 2008.
[10] RUSU R B, BLODOW N, BEETZ M. Fast point feature histograms (FPFH) for 3D registration[C]//IEEE International Conference on Robotics and Automation. Kobe:IEEE, 2009.
[11] GUOY, SOHEL F, BENNAMOUN M, et al. Rotational projection statistics for 3D local surface description and object recognition[J]. International Journal of Computer Vision, 2013, 105(1):63-86.
[12] 陆军, 彭仲涛, 夏桂华. 点云多法向量邻域特征配准算法[J]. 光电子·激光, 2015(4):28.
[13] 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(1):113-120.
[14] 胡修祥, 张良. 结合NARF特征的改进型3D-NDT多视点云配准[J]. 信号处理, 2015, 31(12):1674-1679.
[15] 舒程珣, 何云涛, 孙庆科. 基于卷积神经网络的点云配准方法[J]. 激光与光电子学进展, 2017(3):129-137.
[16] 李仁忠, 杨曼, 田瑜, 等. 基于ISS特征点结合改进ICP的点云配准算法[J]. 激光与光电子学进展, 2017,54(11):312-319.
[17] ZHONG Y. Intrinsic shape signatures:a shape descriptor for 3D object recognition[C]//Proceedings of the 12th IEEE International Conference on Computer Vision Workshops (ICCV Workshops). Kyoto:IEEE, 2009:689-696.
[18] SALTIS, TOMBARI F, DI STEFANO L. SHOT:Unique signatures of histograms for surface and texture description[J]. Computer Vision and Image Understanding, 2014, 125:251-264.
[19] FISCHLER M A. Random sample consensus:a paradigm for model fitting with applications to image analysis and automated cartography[J]. Readings in Computer Vision, 1987:726-740.
[20] PULLI K. Multiview registration for large data sets[C]//Proceedings of the 2nd International Conference on 3D Digital Imaging and Modeling. Ottawa, Ontario:IEEE,1999.
[21] LI Bin. Three dimensional laser point cloud slicing method for calculating irregular Volume[J]. Journal of Geodesy and Geoinformation Science, 2019, 2(4):31-43.

一种基于ISS-SHOT特征的点云配准算法

A point cloud registration algorithm based on ISS-SHOT features

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 14

编辑推荐

Metrics

本文评价

[1]	谢洪, 陈立波, 聂倩, 吴玮, 张沛. 利用点云配准的空地影像融合技术[J]. 测绘通报, 2022, 0(6): 82-87.
[2]	谢元, 董梦, 马新建. 多源数据在复杂场景建筑物三维重建的应用[J]. 测绘通报, 2022, 0(6): 143-147.
[3]	阮明浩, 卢永华, 刘玉贤, 汤圣君, 王伟玺, 张宇琦, 李游. 激光与倾斜点云精确配准与无缝融合[J]. 测绘通报, 2022, 0(4): 6-10.
[4]	赵彦刚, 付守健, 陈宏强, 吴波. Heron移动背包三维激光扫描系统在1∶500大比例尺测图中的精度评价及效率分析[J]. 测绘通报, 2021, 0(10): 114-116.
[5]	杨海舰, 徐二帅, 陈文佳, 许志华. 四元组标靶辅助下的RGB-D室内点云配准[J]. 测绘通报, 2020, 0(12): 32-36.
[6]	袁志聪, 鲁铁定, 刘瑞. 一种基于BFGS修正的正态分布变换点云配准方法[J]. 测绘通报, 2020, 0(10): 38-42.
[7]	李明峰, 陆海芳, 赵湘玉. 对偶四元数法在稳健点云配准中的应用[J]. 测绘通报, 2019, 0(9): 22-26.
[8]	郭雨, 夏永华, 杨明龙. 融合多源测量数据的钟乳石三维建模方法[J]. 测绘通报, 2019, 0(2): 49-53.
[9]	杨铭. 背包式移动三维激光扫描系统的应用[J]. 测绘通报, 2018, 0(9): 91-95.
[10]	刘家良, 孙立双. 结合空间相关性的城市热点路段提取方法[J]. 测绘通报, 2018, 0(6): 73-77.
[11]	杨敏, 甘淑, 袁希平, 高莎, 朱赞, 于辉. 复杂带状地形条件下的地面三维激光扫描点云数据采集与配准处理试验[J]. 测绘通报, 2018, 0(5): 35-40.
[12]	左志强, 黄先锋, 杨冲, 张帆, 高云龙. 基于倾斜影像的城市场景隐式曲面重建[J]. 测绘通报, 2017, 0(12): 21-28.
[13]	赵夫群, 周明全. 基于二维图像特征的点云配准方法[J]. 测绘通报, 2017, 0(10): 39-42,73.
[14]	邹峥嵘邹小丹刘合凤张云生. 基于半全局多视近景影像匹配的三维建模方法[J]. 测绘通报, 2014, 0(2): 34-36.