田朋举,花向红,康停军,王彬

• 1:武汉大学测绘学院
• 2:武汉大学灾害监测和防治研究中心
• 3:佛山市测绘地理信息研究院

摘要(Abstract)：

针对现有大规模点云数据平面特征分割方法中存在的错误识别、效率低、抗噪性差等问题,该文提出一种基于2D霍夫变换和八叉树的建筑物平面精细分割方法。该方法首先,对原始点云进行空间均匀降采样并向X-Y面投影,利用改进的2D霍夫变换算法提取投影后的点云线段,使用选权迭代法精确计算线段所在直线的方程及端点坐标,进一步确定立面的空间几何方程;接下来,建立原始点云数据的八叉树结构,利用端点坐标设计立方体并分割出立方体内的立面点云;最后,将立面点云从原始点云中剔除,对余下点云降采样并向X-Z面投影,重复以上过程分割水平面点云。试验验证了该文方法对建筑物面状特征分割的有效性。

关键词(KeyWords)： 点云;平面特征;霍夫变换;选权迭代法;八叉树

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金项目（41674005,41374011）

作者(Author): 田朋举,花向红,康停军,王彬

DOI: 10.16251/j.cnki.1009-2307.2021.02.018

参考文献(References)：

• [1] HUANG H,BRENNER C,SESTER M.3D building roof reconstruction from point clouds via generative models[C]//The 19th ACM SIGSPATIAL International Symposium on Advances in Geographic Information Systems.New York:ACM,2011.
• [2] LIU X Y,ZHANG Y J,LING X,et al.TopoLAP:topology recovery for building reconstruction by deducing the relationships between linear and planar primitives[J].Remote Sensing,2019,11(11):1372.
• [3] MEEUSSEN W.Autonomous door opening and plugging in with a personal robot[J].Robotics & Automation,2010,2(8):729-736.
• [4] RUSU R B,MEEUSSEN W,CHITTA S,et al.Laser-based perception for door and handle identification[C]∥International Conference on Advanced Robotics.Piscataway:IEEE,2009.
• [5] CHEKHLOV D,GEE A P,CALWAY A,et al.Ninja on a plane:automatic discovery of physical planes for augmented reality using visual SLAM[C]//Proceedings of the 6th IEEE and ACM International Symposium on Mixed and Augmented Reality.Piscataway:IEEE,2007.
• [6] MA K,LU F,CHEN X.Robust planar surface extraction from noisy and semi-dense 3D point cloud for augmented reality[C]//2016 International Conference on Virtual Reality and Visualization(ICVRV).Piscataway:IEEE,2017.
• [7] REMONDINO F.Heritage Recording and 3D modeling with photogrammetry and 3D scanning[J].Remote Sensing,2011,3(6):1104-1138.
• [8] SANCHEZ-APARICIO L J,POZO S D,RAMOS L F,et al.Heritage site preservation with combined radiometric and geometric analysis of TLS data[J].Automation in Construction,2018,85:4-39.
• [9] FISCHLER M A,BOLLES R C.Random sample consensus:a paradigm for model fitting with applications to image analysis and automated cartography[J].Communications of the ACM,1981,24(6):381-395.
• [10] SCHNABEL R,WAHL R,KLEIN R.Efficient RANSAC for point cloud shape detection[J].Computer Graphics Forum,2007,26(2):214-226.
• [11] GALLO O,MANDUCHI R,RAFII A.CC-RANSAC:fitting planes in the presence of multiple surfaces in range data[J].Pattern Recognition Letters,2011,32(3):403-410.
• [12] RAGURAM R,CHUM O,POLLEFEYS M,et al.USAC:a universal framework for random sample consensus[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2013,35(8):2022-2038.
• [13] 张帆,高云龙,黄先锋,等.基于球面投影的单站地面激光点云直线段提取方法[J].测绘学报,2015,44(6):655-662.(ZHANG Fan,GAO Yunlong,HUANG Xianfeng,et al.Spherical projection based straight line segment extraction for single station terrestrial laser point cloud[J].Acta Geodaetica et Cartographica Sinica,2015,44(6):655-662.)
• [14] ABUZAINA A,NIXON M S,CARTER J N.Sphere detection in kinect point clouds via the 3D Hough transform[C]//The 15th International Conference on Computer Analysis of Images and Patterns.Berlin:Springer,2013.
• [15] DROST B,ILIC S.Local Hough transform for 3D primitive detection[C]//International Conference on 3D Vision.Piscataway:IEEE,2015:398-406.
• [16] HULIK R,SPANEL M,SMRZ P,et al.Continuous plane detection in point-cloud data based on 3D Hough Transform[J].Journal of Visual Communication and Image Representation,2014,25(1):86-97.
• [17] DUDA R O,HART P E.Use of the Hough transformation to detect lines and curves in pictures[J].Communications of the ACM,1972,15(1):11-15.
• [18] YLA-JAASKI A,KIRYATI N.Adaptive termination of voting in the probabilistic circular Hough transform[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1994,16(9):911-915.
• [19] OGUNDANA O O,COGGRAVE C R,BURGUETE R L,et al.Automated detection of planes in 3D point clouds using fast Hough transforms[J].Optical Engineering,2011,50(5):053609.
• [20] NGUYEN H H,KIM J,LEE Y,et al.Accurate and fast extraction of planar surface patches from 3D point cloud[C]//Proceedings of the 7th International Conference on Ubiquitous Information Management and Communication.New York:ACM,2013.
• [21] NURUNNABI A,BELTON D,WEST G.Robust segmentation in laser scanning 3D point cloud data[C]∥The 14th International Conference on Digital Image Computing:Techniques and Applications(DICTA’12).Piscataway:IEEE,2012.
• [22] 董震,杨必胜.车载激光扫描数据中多类目标的层次化提取方法[J].测绘学报,2015,44(9):980-987.(DONG Zhen,YANG Bisheng.Hierarchical extraction of multiple objects from mobile laser scanning data[J].Acta Geodaetica et Cartographica Sinica,2015,44(9):980-987.)
• [23] VO A V,TRUONG-HONG L,LAEFER D F,et al.Octree-based region growing for point cloud segmentation[J].ISPRS Journal of Photogrammetry and Remote Sensing,2015,104:88-100.
• [24] 李明磊,李广云,王力,等.采用八叉树体素生长的点云平面提取[J].光学精密工程,2018,26(1):172-183.(LI Minglei,LI Guangyun,WANG Li,et al.Planar feature extraction from unorganized point clouds using octree voxel based region growing[J].Optics and Precision Engineering,2018,26(1):172-183.)
• [25] 张祥甫,刘健,石章松,等.基于深度学习的语义分割问题研究综述[J].激光与光电子学进展,2019,56(15):20-34.(ZHANG Xiangfu,LIU Jian,SHI Zhangsong,et al.Review of deep learning-based semantic segmentation[J].Laser & Optoelectronics Progress,2019,56(15):20-34.)
• [26] SU H,MAJI S,KALOGERAKIS,et al.Multi-view convolutional neural networks for 3D shape recognition[C]//IEEE International Conference on Computer Vision.Piscataway:IEEE,2015:945-953.
• [27] BOULCH A,SAUX B L,AUDEBERT N.Unstructured point cloud semantic labeling using deep segmentation networks[J].Eurographics Workshop on 3D Object Retrieval,2017,2:17-24.
• [28] GUERRY J,BOULCH A,SAUX B L,et al.SnapNet-R:consistent 3D multi-view semantic labeling for robotics[C]//IEEE International Conference on Computer Vision.Piscataway:IEEE,2017:669-678.
• [29] WU Z R,SONG S R,KHOSLA A,et al.3D ShapeNets:a deep representation for volumetric shapes[C]//IEEE Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE,2015:1912-1920.
• [30] LATEEF F,RUICHEK Y.Survey on semantic segmentation using deep learning techniques[J].Neurocomputing,2019,338:321-348.
• [31] GRAHAM B.Spatially-sparse convolutional neural networks[J].Computer Science,2014,34(6):864-867.
• [32] CHARLES R Q,HAO S,MO K,et al.PointNet:deep learning on point sets for 3D classification and segmentation[C]//IEEE Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE,2017:652-660.
• [33] QI C R,YI L,SU H,et al.PointNet++:deep hierarchical feature learning on point sets in a metric space[C]//Advances in Neural Information Processing Systems.[S.l.]:[s.n.],2017:5105-5114.
• [34] LI Y Y,BU R,SUN M C,et al.PointCNN:convolution on X-transformed points[C/OL]//Advances in Neural Information Processing Systems,2018:828-838[2019-09-27].https://arxiv.org/abs/1801.07791.
• [35] 叶珉吕,花向红,陈西江,等.基于正交整体最小二乘平面拟合的点云数据去噪方法研究[J].测绘通报,2013(11):40-42.(YE Minlyu,HUA Xianghong,CHEN Xijiang,et al.Research on method for the denoising of point cloud based on orthogonal TLS fitting[J].Bulletin of Surveying and Mapping,2013(11):40-42.)
• [36] 王晏民,胡春梅.一种地面激光雷达点云与纹理影像稳健配准方法[J].测绘学报,2012,41(2):266-272.(WANG Yanmin,HU Chunmei.A robust registration method for terrestrial LiDAR point clouds and texture image[J].Acta Geodaetica et Cartographica Sinica,2012,41(2):266-272.)
• [37] RUSU R B,COUSINS S.3D is here:point cloud library(PCL)[C]//IEEE International Conference on Robotics and Automation.Piscataway:IEEE,2011.