车载激光扫描数据的高速道路自动提取方法Automated extracting highway from mobile laser scanning point clouds
胡啸,黄明,周海霞
摘要(Abstract)：
针对车载激光扫描技术存在数据量大、点云散乱、目标复杂以及地物相互遮挡等问题,该文提出一种从车载激光扫描数据中高速道路自动提取方法。①对激光点云进行基于扫描线的自适应滤波,剔除路面点。②对于滤波后激光点云数据,使用平滑度约束下的欧式聚类算法进行聚类。③对道路边界进行优化追踪,提取出完整的道路边界和道路面。实验结果表明,本文方法能够快速准确地提取高速公路道路边界和路面点云,提取结果的准确率、完整率和检测质量分别为97.52%、94.23%和92.69%。
关键词(KeyWords)： 车载激光点云;道路点云提取;点云滤波;平滑度约束;欧式聚类
基金项目(Foundation): 国家自然科学基金项目(41501494,41601409);; 北京市自然科学基金项目(8172016)
作者(Author): 胡啸,黄明,周海霞
DOI: 10.16251/j.cnki.1009-2307.2019.03.017
参考文献(References)：
- [1]李德仁,姚远,邵振峰.智慧城市中的大数据[J].武汉大学学报(信息科学版),2014,39(6):1-12.(LI Deren,YAO Yuan,SHAO Zhenfeng.Big data in smart city[J].Geomatics and Information Science of WuhanUniversity,2014,39(6):1-12.)
- [2]ZHOU J,CHENG L,BISCHOF W F.Online learningwith novelty detection in human-guided road tracking[J].IEEE Transactions on Geoscience &RemoteSensing,2007,45(12):3967-3977.
- [3]BARSI A,HEIPKE C.Artificial neural networks forthe detection of road junctions in aerial images[J].Geological Magazine,2008,70(2):180-182.
- [4]陈昌鸣,向煜,龙川.基于车载激光雷达的行道树提取研究[J].北京测绘,2015(1):18-21.(CHEN Changming,XIANG Yu,LONG Chuan.The research of street treesextraction based on vehicle-borne LiDAR[J].BeijingSurveying and Mapping,2015(1):18-21.)
- [5]AXELSSON P.DEM generation from laser scannerdata using adaptive TIN models[C]∥InternationalArchives of Photogrammetry &Remote Sensing.[S.l.:s.n.],2000.
- [6]KOBLER A,PFEIFER N,OGRINC P,et al.Repetitiveinterpolation:a robust algorithm for DTM generationfrom aerial laser scanner data in forested terrain[J].Remote Sensing of Environment,2007,108(1):9-23.
- [7]ZHANG J,LIN X,NING X.SVM-based classificationof segmented airborne LiDAR point clouds in urbanareas[J].Remote Sensing,2013,5(8):3749-3775.
- [8]NIEMEYER J,ROTTENSTEINER F,SOERGEL U.Contextual classification of LiDAR data and buildingobject detection in urban areas[J].ISPRS Journal ofPhotogrammetry &Remote Sensing,2014,87(1):152-165.
- [9]SOHN G,DOWMAN I.Data fusion of high-resolutionsatellite imagery and LiDAR data for automatic buildingextraction[J].ISPRS Journal of Photogrammetry &Remote Sensing,2007,62(1):43-63.
- [10]QIN R,FANG W.A hierarchical building detection methodfor very high resolution remotely sensed images combinedwith DSM using graph cut optimization[J].Photo-grammetric Engineering &Remote Sensing,2014,80(9):37-47.
- [11]ZHONG R,WEI J,SU W,et al.A method for extractingtrees from vehicle-borne laser scanning data[J].Mathematical &Computer Modelling,2013,58(3/4):727-736.
- [12]PU S,RUTZINGER M,VOSSELMAN G,et al.Recognizing basic structures from mobile laser scanningdata for road inventory studies[J].ISPRS Journal ofPhotogrammetry &Remote Sensing,2011,66(S6):28-39.
- [13]BRENNER C.Extraction of features from mobile laserscanning data for future driver assistance systems[J].2009,49(2):25-42.
- [14]MANANDHAR D,SHIBASAKI R.Auto-extraction ofurban features from vehicle-borne laser data[EB/OL].[2018-06-22].http:∥pdfs.semanticscholar.org/2a9f/19787f3652bbc3f21213175b872aae4923bc.pdf.
- [15]ABUHADROUS I,AMMOUN S,NASHASHIBI F,et al.Digitizing and 3Dmodeling of urban environmentsand roads using vehicle-borne laser scanner system[C]∥IEEE/RSJ International Conference on IntelligentRobots and Systems.Sendai,Japan:IEEE,2016:76-81.
- [16]ANTTONI J,JUHA H,HANNU H,et al.Retrievalalgorithms for road surface modelling using laser-basedmobile mapping[J].Sensors,2008,8(9):5238.
- [17]BOYKO A,FUNKHOUSER T.Extracting roads fromdense point clouds in large scale urban environment[J].ISPRS Journal of Photogrammetry &Remote Sensing,2011,66(6):S2-S12.
- [18]ZHANG W.LiDAR-based road and road-edge detection[C]∥Intelligent Vehicles Symposium.San Diego:IEEE,2010:845-848.
- [19]方莉娜,杨必胜.车载激光扫描数据的结构化道路自动提取方法[J].测绘学报,2013,42(2):260-267.(FANG Lina,YANG Bisheng.Automated extractingstructural roads from mobile laser scanning pointclouds[J].Acta Geodaetica et Cartographica Sinica,2013,42(2):260-267.)
- [20]WANG Z,BOVIK A C,SHEIKH H R,et al.Imagequality assessment:from error visibility to structuralsimilarity[J].IEEE Trans Image Process,2004,13(4):600-612.