杨威,万幼川,何培培

• 1:武汉大学遥感信息工程学院

摘要(Abstract)：

针对机载LiDAR目标提取中建筑物与树木难以有效区分的问题,该文提出了一种基于坡度自适应穿透率和张量投票的建筑物检测方法。在利用滤波和高差阈值去除地面点和矮小地物点的基础上,采用坡度自适应穿透率作为区分建筑物和植被的主要特征,较好地突出了建筑物点和树木点在空间分布上的密度差异;设计基于张量投票的投票算法,对坡度自适应穿透率特征进行邻域投票,以促进相邻点之间特征信息的传递,增强了该特征对于植被和建筑物的可分性。采用ISPRS提供的测试数据进行实验,结果表明,该方法能有效地区分建筑物和树木点,提取的建筑物完整度达94.6%,准确度达98.3%。

关键词(KeyWords)： 建筑物提取;机载LiDAR;穿透率;张量投票

Abstract:

Keywords:

基金项目(Foundation): 国家科技支撑项目(2014BAL05B07)

作者(Author): 杨威,万幼川,何培培

DOI: 10.16251/j.cnki.1009-2307.2016.09.002

参考文献(References)：

• [1]AWRANGJEB M,FRASER S.Automatic segmentation of raw LiDAR data for extraction of building roofs[J].Remote Sensing,2014,6(5):3716-3751.
• [2]ROTTENSTEINER F,SOHN G,GERKE M,et al.Results of the ISPRS benchmark on urban object detection and 3Dbuilding reconstruction[J].Isprs Journal of Photogrammetry&Remote Sensing,2014,93(7):256-271.
• [3]罗伊萍,姜挺,王鑫,等.支持向量机的建筑物激光脚点提取方法[J].测绘科学,2011,36(4):173-175.
• [4]NIEMEYER J,ROTTENSTEINER F,SOERGEL U.Classification of urban LiDAR data using conditional random field and random forests[C]//Urban Remote Sensing Event Joint.IEEE,2013:139-142.
• [5]徐文学,杨必胜,董震,等.标记点过程用于点云建筑物提取[J].武汉大学学报:信息科学版,2014,39(5):520-525.
• [6]MONGUS D,LUKAC N,ZALIK B.Ground and building extraction from LiDAR data based on differential morphological profiles and locally fitted surfaces[J].Isprs Journal of Photogrammetry&Remote Sensing,2014,93(7):145-156.
• [7]XU Jingzhong,WANG Youchuan,YAO Fang.A method of 3D building boundary extraction from airborne LiDAR points cloud[J].Symposium on Photonics&Optoelectronic,2010:1-4.
• [8]任自珍,岑敏仪,张同刚,等.LiDAR数据中建筑物提取的新方法:Fc-S法[J].测绘科学,2010,35(6):134-136.
• [9]AXELSSON P.DEM generation from laser scanner data using adaptive TIN models[J].Proceedings of the19th ISPRS Conference,IAPRS,2000,33.
• [10]RUTZINGER M,HOFLE B,HOLLAUS M,et al.Object-based point cloud analysis of full-waveform airborne laser scanning data for urban vegetation classification[J].Sensors,2008,8(8):4505-4528.
• [11]FILIN S,PFELFER N.Neighborhood systems for airborne laser data[J].Photogrammetric Engineering&Remote Sensing,2005,71(6):743-755.
• [12]HOFLE B,MüCKE W,DUTTER M,et al.Detection of building regions using airborne LiDAR:A new combination of raster and point cloud based gis methods[C]//In A.Car,G.Griesebner,J.Strobl(Eds.),Geospatial crossroads at GI forum’09:Proceedings of the Geoinformatics Forum Salzburg.Salzburg,Austria,2009:66-75.
• [13]MORDOHAI P,MEDIONI G.Tensor voting:A perceptual organization approach to computer vision and machine learning[C]//Synthesis Lectures on Image Video&Multimedia Processing,2006:136.
• [14]SAMPATH A,SHAN J.Segmentation and reconstruction of polyhedral building roofs from aerial LiDAR point clouds[J].IEEE Transactions on Geoscience&Remote Sensing,2010,48(3):1554-1567.
• [15]SHAN J.Building boundary tracing and regularization from airborne lidar point clouds[J].Photogrammetric Engineering&Remote Sensing,2007,73(7):805-812.
• [16]ISPRS.Web site of the ISPRS test project on urban classification and 3Dbuilding reconstruction[EB/OL].(2013-12-12)[2015-04-25].http://www2.isprs.org/commissions/comm3/wg4/tests.html.
• [17]ISPRS.Web site of the ISPRS test project on urban classification and 3D building reconstruction:Results[EB/OL].(2015-04-20)[2015-04-25].http://www2.isprs.org/commissions/comm3/wg4/results/a2_detect.html.