LiDAR point cloud segmentation algorithm based on supervoxel and pairwise linkage clustering

doi:10.13474/j.cnki.11-2246.2022.0079

Abstract

Abstract: Aiming at the problems of poor robustness and low efficiency of existing LiDAR point cloud segmentation algorithms,this paper proposes a new hierarchical clustering segmentation algorithm.Firstly,a supervoxel with adaptive resolution is generated from the LiDAR point clouds.Then an improved pairwise linkage segmentation algorithm is used to the supervoxel to get the segmentation results.Experimental results show that the proposed segmentation algorithm has better robustness and higher computational efficiency compared with that of the existing segmentation methods.The issues of over segmentation and insufficient segmentation of the point clouds have been solved.The proposed algorithm is more prominent in segmentation details,and the segmentation results can effectively ensure the accuracy of subsequent data processing.

Key words: LiDAR point cloud;supervoxel;pairwise linkage;segmentation;robustness

CLC Number:

PU Dongdong, DING Haiyong. LiDAR point cloud segmentation algorithm based on supervoxel and pairwise linkage clustering[J]. Bulletin of Surveying and Mapping, 2022, 0(3): 65-69.

References

[1] MIAO W, YI S T. Incremental segmentation of LiDAR point clouds with an octree:structured voxel space[J]. The Photogrammetric Record,2011,26(133):32-57.
[2] GRILLI E, MENNA F, REMONDINO F. A review of point clouds segmentation and classification algorithms[J]. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2017, XLII-2/W3:339-344.
[3] CASTILLO E, LIANG J, ZHAO H. Point cloud segmentation and denoising via constrained nonlinear least squares normal estimates[M]. Springer Berlin Heidelberg:Innovations for Shape Analysis, 2013.
[4] JAGANNAATHAN A, MILLER E L. Three-dimensional surface mesh segmentation using curvedness-based region growing approach[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(12):2195-2204.
[5] CAMURRI M, VEZZANI R, CUCCHIARA R. 3D Hough transform for sphere recognition on point clouds[J]. Machine Vision and Applications,2014,25(7):1877-1891.
[6] 邹鹏,李蓓智,龚菊贤,等.改进的RANSAC点云分割算法及其应用[J].机械设计与制造, 2020,357(11):128-131.
[7] 孙红岩,孙晓鹏,李华.基于K-means聚类方法的三维点云模型分割[J].计算机工程与应用, 2006, 42(10):42-45.
[8] 王晓辉,吴禄慎,陈华伟,等.应用改进的粒子群优化模糊聚类实现点云数据的区域分割[J].光学精密工程,2017,25(4):1095-1105.
[9] 曹晓叶,王知衍,梁英宏,等.基于均值漂移聚类的点模型简化方法[J].计算机应用, 2008, 28(4):963-965.
[10] 李明磊,刘少创,杨欢,等.双层优化的激光雷达点云场景分割方法[J].测绘学报,2018, 47(2):269-274.
[11] VIEIRA M, SHIMADA K. Surface mesh segmentation and smooth surface extraction through region growing[J]. Computer Aided Geometric Design,2005,22(8):771-792.
[12] ZHOU Y, WANG D, XIE X, et al. A fast and accurate segmentation method for ordered LiDAR point cloud of large-scale scenes[J]. IEEE Geoscience and Remote Sensing Letters,2014, 11(11):1981-1985.
[13] 袁华,庞建铿,莫建文.基于体素化网格下采样的点云简化算法研究[J].电视技术,2015,39(17):43-47.
[14] 黄镇,韩慧妍,韩燮.结合超体素几何和色彩信息的快速三维点云分割[J].中国科技论文, 2018, 13(2):157-161.
[15] PAPON J, ABRAMOV A, SCHOELER M, et al. Voxel cloud connectivity segmentation-supervoxels for point clouds[C]//Proceedings of 2013 IEEE Conference on Computer Vision and Pattern Recognition. Portland:IEEE,2013:2027-2034.
[16] LIN Y, WANG C, ZHAI D, et al. Toward better boundary preserved supervoxel segmentation for 3D point clouds[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2018, 143:39-47.
[17] LU X, YAO J, TU J, et al. pairwise linkage for point cloud segmentation[C]//Proceedings of 2016 ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences. Prague:ISPRS Congress, 2016:201-208.
[18] 浮丹丹,周绍光,徐洋,等.基于主成分分析的点云平面拟合技术研究[J].测绘工程,2014,23(4):20-23.
[19] 周炳南,闵华松,康雅文. PCL环境下的三维点云分割算法研究[J].微电子学与计算机,2018, 35(6):101-105.
[20] 吴燕雄,李峰,刘芳,等.平滑度欧氏聚类算法分割点云数据[J].测控技术,2016,35(3):41-43.