适用于激光点云配准的重叠区域提取方法

王帅; 孙华燕; 郭惠超

doi:10.3788/IRLA201746.S126002

适用于激光点云配准的重叠区域提取方法

doi: 10.3788/IRLA201746.S126002

1.
装备学院研究生院,北京 101416;
2.
装备学院光电装备系,北京 101416

基金项目:

国家自然科学基金（61302183）

详细信息

作者简介:
王帅(1991-),男,博士生,主要从事激光三维成像及激光雷达系统方面的研究。Email:mage1120@foxmail.com

中图分类号: TN249

Overlapping region extraction method for laser point clouds registration

1.
Department of Postgraduate,The Academy of Equipment,Beijing 101416,China;
2.
Department of Optical and Electrical Equipment,The Academy of Equipment,Beijing 101416,China

摘要: 多视角激光点云的配准是目标三维重建的基础，而点云之间重叠区域的提取对提高配准效率具有重要意义。提出了一种基于区域分割的重叠区域提取方法，首先使用谱聚类按照几何结构特征对各视角点云区域分割，然后对各个区域建立ESF多维形状描述符。对提取的描述符计算两两之间的欧式距离，描述符之间欧式距离最近的区域即为点云之间的重叠区域。实验证明：算法对激光点云噪声及初始位姿等因素表现稳定，在点云采集视角差异较大的情况下仍能完成重叠区域的提取。在仿真的四组点云测试中，点云的重叠率平均提高了14.3%，在实际采集的多视角点云测试中，点云的重叠率平均提高了13.3%。
- 激光三维成像 /
- 点云配准 /
- 谱聚类 /
- ESF
Abstract: Multi-view laser point cloud registration is the basis of three dimension reconstruction, and the extraction of overlapping regions in multi-viewpoint laser point clouds is of great values to improve the efficiency of laser point cloud registration. A method of overlapping regions extraction based on region segmentation was presented, the spectral clustering was used to segment the point clouds of each viewpoint according to the geometric structure, and then a multi-dimensional shape descriptor was created for each region. The Euclidean distances were calculated for each extracted descriptor, the area with nearest Euclidean distance between descriptors was the overlapping area between point clouds. Experiments show that the algorithm is stable to the laser point clouds noise and the initial position, and the algorithm could still complete the extraction of overlapping regions in the case of large differences between point clouds. With the simulated multi-viewpoint point clouds, the overlap ratio increased by an average of 14.3%. And with the actual multi-viewpoint point clouds, the overlap ratio increased by an average of 13.3%.
- laser 3D imaging /
- point cloud registration /
- spectral clustering /
- ESF

[1]	Liu Yu, Chen Feng, Wang Ying, et al. Measurement of relative position and pose between two spacecrafts based on laser lidar[J]. Infrared and Laser Engineering, 2016, 45(8):0817003. (in Chinese)刘玉, 陈凤, 王盈,等. 基于激光雷达的航天器相对位姿测量技术[J]. 红外与激光工程, 2016, 45(8):0817003.
[2]	Fan Youcheng, Zhao Hongli, Sun Huayan, et al. Application of cross-correlation algorithm in moving target range-gated three-dimensional laser active imaging[J]. Infrared and Laser Engineering, 2016, 45(6):0617003. (in Chinese)范有臣, 赵洪利, 孙华燕,等. 互相关算法在运动目标距离选通激光三维成像中的应用[J]. 红外与激光工程, 2016, 45(6):0617003.
[3]	Rusu R B, Blodow N, Beetz M. Fast Point Feature Histograms (FPFH) for 3D registration[C]//IEEE International Conference on Robotics and Automation, 2009:1848-1853.
[4]	Wei Hu, Zhang Liyan, Liu Shenglan, et al. An algorithm on registration of multi-view range images based on SIFT feature matching[J]. Journal of Computer-Aided Design Computer Graphics, 2010, 22(4):654-661. (in Chinese)韦虎, 张丽艳, 刘胜兰, 等. 基于SIFT图像特征匹配的多视角深度图配准算法[J]. 计算机辅助设计与图形学学报, 2010, 22(4):654-661.
[5]	Chen Maolin, Lu Weixin, Wan Youchuan, et al. Automatic registration of terrestrial point clouds without additional information[J]. Chinese Journal of Lasers, 2016, 43(4):0414003. (in Chinese)陈茂霖, 卢维欣, 万幼川, 等. 无附加信息的地面激光点云自动拼接方法[J]. 中国激光, 2016, 43(4):0414003.
[6]	Dai Yucheng, Zhang Aiwu. Research on fast registration of 3D laser scanning data[J]. Bulletin of Surveying and Mapping, 2010(6):8-11. (in Chinese)戴玉成, 张爱武. 三维激光扫描数据快速配准算法研究[J]. 测绘通报, 2010(6):8-11.
[7]	Sun Nan. Research on the key techniques of quad-nocular stereo measurement[D]. Nanjing:Nanjing University of Aeronautics and Astronautics, 2012. (in Chinese)孙楠. 四目立体测量中的关键技术研究[D]. 南京:南京航空航天大学, 2012.
[8]	Zhang Xiaojuan, Li Zhongke, Wang Xianze, et al. Registration of point clouds data based on genetic algorithm[J]. Computer Engineering, 2012, 38(21):214-217. (in Chinese)张晓娟, 李忠科, 王先泽,等. 基于遗传算法的点云数据配准[J]. 计算机工程, 2012, 38(21):214-217.
[9]	Shen Yinghua, Li Zhuojia, Yang Cheng, et al. Point cloud registration with normal feature histogram[J]. Optics and Precision Engineering, 2015, 23(10z):591-598. (in Chinese)沈萦华, 李卓嘉, 杨成,等. 基于法向特征直方图的点云配准算法[J]. 光学精密工程, 2015, 23(10z):591-598.
[10]	Liu Bin, Guo Jiming, Deng Xiangxiang. A point cloud registration method based on Octree and ICP[J]. Science of Surveying Mapping, 2016, 41(2):130-132. (in Chinese)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.
[11]	Liu Xin. Research on registration algorithm of three dimensional point cloud[D]. Qinhuangdao:Yanshan University, 2015. (in Chinese)刘新. 三维点云数据的配准算法研究[D]. 秦皇岛:燕山大学, 2015.
[12]	Han Baochang, Cao Junjie, Su Zhixun. Automatic point clouds registration based on regions[J]. Journal of Computer-Aided Design and Computer Graphics, 2015, 27(2):313-319. (in Chinese)韩宝昌, 曹俊杰, 苏志勋. 一种区域层次上的自动点云配准算法[J]. 计算机辅助设计与图形学学报, 2015, 27(2):313-319.
[13]	Tipping M E, Bishop C M. Mixtures of probabilistic principal component analyzers.[J]. Neural Computation, 1999, 11(2):443.
[14]	Han Li, Xu Jianguo, Li Lin, et al. 3D shape analysis based on Laplacian multi-eigenmap[J]. Journal of Computer-Aided Design and Computer Graphics, 2015, 27(11):2142-2148. (in Chinese)韩丽, 徐建国, 黎琳,等. Laplacian多特征映射的三维模型形状分析[J]. 计算机辅助设计与图形学学报, 2015, 27(11):2142-2148.
[15]	Krishnamurthy V, Levoy M. Fitting smooth surfaces to dense polygon meshes[C]//Conference on Computer Graphics and Interactive Techniques, ACM, 1996:313-324.

[1]	杨耘, 江万成, 任超锋, 马正龙, 蒲禹池, 焦宇航. 倾斜影像辅助的无人机载LiDAR高陡边坡形变监测 . 红外与激光工程, 2023, 52(2): 20220373-1-20220373-8. doi: 10.3788/IRLA20220373
[2]	王明军, 易芳, 李乐, 黄朝军. 自适应局部邻域特征点提取和匹配的点云配准 . 红外与激光工程, 2022, 51(5): 20210342-1-20210342-10. doi: 10.3788/IRLA20210342
[3]	王春阳, 李国瑞, 刘雪莲, 施春皓, 丘文乾. 基于IVCCS的三维点云配准算法 . 红外与激光工程, 2022, 51(6): 20210491-1-20210491-12. doi: 10.3788/IRLA20210491
[4]	赵毅强, 艾西丁·艾克白尔, 陈瑞, 周意遥, 张琦. 基于体素化图卷积网络的三维点云目标检测方法 . 红外与激光工程, 2021, 50(10): 20200500-1-20200500-9. doi: 10.3788/IRLA20200500
[5]	李鑫, 莫思特, 黄华, 杨世基. 自动计算重叠度的多源点云配准方法 . 红外与激光工程, 2021, 50(12): 20210088-1-20210088-9. doi: 10.3788/IRLA20210088
[6]	崔文弢, 焦卫东, 庞艳丽. 基于几何代数的SVS-NLMS点云配准算法 . 红外与激光工程, 2021, 50(12): 20210115-1-20210115-10. doi: 10.3788/IRLA20210115
[7]	卢祺, 林婷婷, 李程鹏, 李荣华, 葛研军. 空间非合作目标点云聚类配准方法 . 红外与激光工程, 2021, 50(9): 20200431-1-20200431-10. doi: 10.3788/IRLA20200431
[8]	王建军, 卢云鹏, 张荠匀, 白崇岳, 胡燕威, 李旭辉, 王炯宇. 实现激光点云高效配准的ICP优化及性能验证 . 红外与激光工程, 2021, 50(10): 20200483-1-20200483-7. doi: 10.3788/IRLA20200483
[9]	孙建波, 潘幸华, 杨良, 陈万春, 赵育善. 滑翔飞行器线性伪谱模型预测控制三维轨迹规划 . 红外与激光工程, 2020, 49(9): 20200279-1-20200279-7. doi: 10.3788/IRLA20200279
[10]	葛鹏, 郭静菁, 陈丛, 尚震, 樊彦恩, 盛磊. 基于盖革APD阵列的光子计数三维成像 . 红外与激光工程, 2020, 49(3): 0305007-0305007-8. doi: 10.3788/IRLA202049.0305007
[11]	薛珊, 吕南方, 沈雨鹰, 刘正彬, 郭建波. 基于激光三维点云的机械工件识别方法 . 红外与激光工程, 2019, 48(4): 442002-0442002(8). doi: 10.3788/IRLA201948.0442002
[12]	刘波, 赵娟莹, 眭晓林, 曹昌东, 颜子恒, 吴姿妍. 阵列分束激光三维成像技术 . 红外与激光工程, 2019, 48(6): 606001-0606001(6). doi: 10.3788/IRLA201948.0606001
[13]	王鹏, 杨文超, 孙长库, 郭世珍. 舌面彩色三维点云的舌体分割及舌裂纹提取 . 红外与激光工程, 2017, 46(S1): 82-89. doi: 10.3788/IRLA201746.S117004
[14]	武奕楠, 李国宁, 张柯, 张宇, 金龙旭. 基于同名点追踪的空间相机成像拼接配准模型 . 红外与激光工程, 2016, 45(3): 326002-0326002(7). doi: 10.3788/IRLA201645.0326002
[15]	邵春艳, 丁庆海, 罗海波, 李玉莲. 采用高维数据聚类的目标跟踪 . 红外与激光工程, 2016, 45(4): 428002-0428002(10). doi: 10.3788/IRLA201645.0428002
[16]	刘玉, 陈凤, 王盈, 黄建明, 魏祥泉. 基于激光雷达的航天器相对位姿测量技术 . 红外与激光工程, 2016, 45(8): 817003-0817003(6). doi: 10.3788/IRLA201645.0817003
[17]	侯佳, 何志平, 舒嵘. 离轴三反光纤阵列激光三维成像发射系统 . 红外与激光工程, 2016, 45(4): 406001-0406001(5). doi: 10.3788/IRLA201645.0406001
[18]	陈骁, 石志广, 杨卫平, 凌建国. 利用三维点云的圆锥状弹头目标参数估计 . 红外与激光工程, 2014, 43(10): 3480-3485.
[19]	胡晓彤, 王建东. 基于子空间特征向量的三维点云相似性分析 . 红外与激光工程, 2014, 43(4): 1316-1321.
[20]	曹忆南, 王新伟, 周燕. 距离选通激光成像空间定位模糊C均值聚类分割法 . 红外与激光工程, 2013, 42(10): 2682-2686,2696.

点击查看大图

计量

文章访问数: 400
HTML全文浏览量: 45
PDF下载量: 94
被引次数: 0

姓名
邮箱
手机号码
标题
留言内容
验证码

留言板

适用于激光点云配准的重叠区域提取方法

doi: 10.3788/IRLA201746.S126002

作者简介:
王帅(1991-),男,博士生,主要从事激光三维成像及激光雷达系统方面的研究。Email:mage1120@foxmail.com

Overlapping region extraction method for laser point clouds registration

计量

适用于激光点云配准的重叠区域提取方法

doi: 10.3788/IRLA201746.S126002

1. 装备学院研究生院,北京 101416;

2. 装备学院光电装备系,北京 101416

作者简介:
王帅(1991-),男,博士生,主要从事激光三维成像及激光雷达系统方面的研究。Email:mage1120@foxmail.com

English Abstract

Overlapping region extraction method for laser point clouds registration

1. Department of Postgraduate,The Academy of Equipment,Beijing 101416,China;

2. Department of Optical and Electrical Equipment,The Academy of Equipment,Beijing 101416,China

全文HTML

目录

留言板

适用于激光点云配准的重叠区域提取方法

doi: 10.3788/IRLA201746.S126002

作者简介: 王帅(1991-),男,博士生,主要从事激光三维成像及激光雷达系统方面的研究。Email:mage1120@foxmail.com

Overlapping region extraction method for laser point clouds registration

计量

出版历程

适用于激光点云配准的重叠区域提取方法

doi: 10.3788/IRLA201746.S126002

1. 装备学院 研究生院,北京 101416; 2. 装备学院 光电装备系,北京 101416

作者简介: 王帅(1991-),男,博士生,主要从事激光三维成像及激光雷达系统方面的研究。Email:mage1120@foxmail.com

English Abstract

Overlapping region extraction method for laser point clouds registration

1. Department of Postgraduate,The Academy of Equipment,Beijing 101416,China; 2. Department of Optical and Electrical Equipment,The Academy of Equipment,Beijing 101416,China

全文HTML

目录

作者简介:
王帅(1991-),男,博士生,主要从事激光三维成像及激光雷达系统方面的研究。Email:mage1120@foxmail.com

1. 装备学院研究生院,北京 101416;

2. 装备学院光电装备系,北京 101416

作者简介:
王帅(1991-),男,博士生,主要从事激光三维成像及激光雷达系统方面的研究。Email:mage1120@foxmail.com

1. Department of Postgraduate,The Academy of Equipment,Beijing 101416,China;

2. Department of Optical and Electrical Equipment,The Academy of Equipment,Beijing 101416,China