Three-dimensional point cloud plane segmentation in both structured and unstructured environments

被引:84
|
作者
Xiao, Junhao [1 ]
Zhang, Jianhua [2 ]
Adler, Benjamin [1 ]
Zhang, Houxiang [3 ]
Zhang, Jianwei [1 ]
机构
[1] Univ Hamburg, Dept Comp Sci, Hamburg, Germany
[2] Zhejiang Univ Technol, Coll Comp Sci & Technol, Hangzhou, Zhejiang, Peoples R China
[3] Alesund Univ Coll, Fac Maritime Technol & Operat, Alesund, Norway
关键词
3D point cloud; Plane segmentation; Region growing; 3D; REGISTRATION; INDOOR; MAPS;
D O I
10.1016/j.robot.2013.07.001
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
This paper focuses on three-dimensional (3D) point cloud plane segmentation. Two complementary strategies are proposed for different environments, i.e., a subwindow-based region growing (SBRG) algorithm for structured environments, and a hybrid region growing (HRG) algorithm for unstructured environments. The point cloud is decomposed into subwindows first, using the points' neighborhood information when they are scanned by the laser range finder (LRF). Then, the subwindows are classified as planar or nonplanar based on their shape. Afterwards, only planar subwindows are employed in the former algorithm, whereas both kinds of subwindows are used in the latter. In the growing phase, planar subwindows are investigated directly (in both algorithms), while each point in nonplanar subwindows is investigated separately (only in HRG). During region growing, plane parameters are computed incrementally when a subwindow or a point is added to the growing region. This incremental methodology makes the plane segmentation fast. The algorithms have been evaluated using real-world datasets from both structured and unstructured environments. Furthermore, they have been benchmarked against a state-of-the-art point-based region growing (PBRG) algorithm with regard to segmentation speed. According to the results, SBRG is 4 and 9 times faster than PBRG when the subwindow size is set to 3 x 3 and 4 x 4 respectively; HRG is 4 times faster than PBRG when the subwindow size is set to 4 x 4. Open-source code for this paper is available at https://github.com/junhaoxiao/TAMS-Planar-Surface-Based-Perception.git. (C) 2013 Elsevier B.V. All rights reserved.
引用
收藏
页码:1641 / 1652
页数:12
相关论文
共 50 条
  • [1] Point Cloud Segmentation Based on Three-Dimensional Shape Matching
    Zhang Kun
    Qiao Shiquan
    Zhou Wanzhen
    [J]. LASER & OPTOELECTRONICS PROGRESS, 2018, 55 (12)
  • [2] Three-Dimensional Point Cloud Semantic Segmentation for Cultural Heritage: A Comprehensive Review
    Yang, Su
    Hou, Miaole
    Li, Songnian
    [J]. REMOTE SENSING, 2023, 15 (03)
  • [3] Learning multiscale spatial context for three-dimensional point cloud semantic segmentation
    Wang, Yang
    Xiao, Shunping
    [J]. JOURNAL OF ELECTRONIC IMAGING, 2020, 29 (06)
  • [4] Three-dimensional point cloud segmentation using a combination of RANSAC and clustering methods
    Singh, Puyam S.
    Nongsiej, Iainehborlang M.
    Marboh, Valarie
    Chutia, Dibyajyoti
    Saikhom, Victor
    Aggarwal, S. P.
    [J]. CURRENT SCIENCE, 2023, 124 (04): : 434 - 441
  • [5] Three-Dimensional Point Cloud Segmentation Algorithm Based on Improved Region Growing
    Li Renzhong
    Liu Yangyang
    Yang Man
    Zhang Huanhuan
    [J]. LASER & OPTOELECTRONICS PROGRESS, 2018, 55 (05)
  • [6] Pose Estimation of Three-Dimensional Face Point Cloud Based on Symmetry Plane
    Ma Zeqi
    Shi Zhiliang
    Li Xiaoyao
    Cai Wangyue
    [J]. LASER & OPTOELECTRONICS PROGRESS, 2022, 59 (08)
  • [7] Planar Segment Based Three-dimensional Point Cloud Registration in Outdoor Environments
    Xiao, Junhao
    Adler, Benjamin
    Zhang, Jianwei
    Zhang, Houxiang
    [J]. JOURNAL OF FIELD ROBOTICS, 2013, 30 (04) : 552 - 582
  • [8] Three-Dimensional Point Cloud Segmentation Algorithm Based on Depth Camera for Large Size Model Point Cloud Unsupervised Class Segmentation
    Fang, Kun
    Xu, Kaiming
    Wu, Zhigang
    Huang, Tengchao
    Yang, Yubang
    [J]. SENSORS, 2024, 24 (01)
  • [9] Coarsening of three-dimensional structured and unstructured grids for subsurface flow
    Aarnes, Jorg Espen
    Hauge, Vera Louise
    Efendiev, Yalchin
    [J]. ADVANCES IN WATER RESOURCES, 2007, 30 (11) : 2177 - 2193
  • [10] Virtual structured-light three-dimensional point cloud compression with geometric reshaping
    Wu, Yingchun
    Qi, Huimin
    Liang, Jie
    Peng, Kuang
    Wang, Anhong
    [J]. JOURNAL OF ELECTRONIC IMAGING, 2022, 31 (02) : 23012