An improved RANSAC algorithm for building point clouds segmentation in consideration of roof structure
LI Yunfan1, TAN Debao1, LIU Rui2,3, WU Jianwei4,5
1. Yangtze River Scientific Research Institute, Wuhan 430010, China;
2. Shenzhen Graduate School, Harbin Institute of Technology, Shenzhen 518055,China;
3. Center for Assessment and Development of Real Estate, Shenzhen 518040, China;
4. Beijing Key Laboratory of Urban Spatial Information Engineering, Beijing 100830, China;
5. School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430029, China
An improved RANSAC algorithm was proposed for point cloud segmentation and geometric primitives extraction of buildings with multiple facets and complex roof structures, including two innovations. Firstly, the “split-segment” strategy combined with regional growth concept is proposed to improve the segment result and efficiency of classic RANSAC algorithm; Secondly, an improved RANSAC algorithm with variant consensus set threshold is presented. By automatically adjusting the consensus set threshold value, geometric primitives with scale difference are likely to meet the validity test, thus avoiding the over-segmentation and under- segmentation problems of classic RANSAC algorithm with fixed consensus set threshold.
李云帆, 谭德宝, 刘瑞, 邬建伟. 顾及建筑物屋顶结构的改进RANSAC点云分割算法[J]. 国土资源遥感, 2017, 29(4): 20-25.
LI Yunfan, TAN Debao, LIU Rui, WU Jianwei. An improved RANSAC algorithm for building point clouds segmentation in consideration of roof structure. REMOTE SENSING FOR LAND & RESOURCES, 2017, 29(4): 20-25.
[1] Sapkota P P.Segmentation of Coloured Point Cloud Data[D].Endchede,The Netherlands:International Institute for Geo-Information Science and Earth Observation,2008:67.
[2] Filin S,Pfeifer N.Segmentation of airborne laser scanning data using a slope adaptive neighborhood[J].ISPRS Journal of Photogrammetry and Remote Sensing,2006,60(2):71-80.
[3] 程 亮,龚健雅.LiDAR辅助下利用超高分辨率影像提取建筑物轮廓方法[J].测绘学报,2008,37(3):391-393.
Cheng L,Gong J Y.Building boundary extraction using very high resolution images and LiDAR[J].Acta Geodaetica et Cartographica Sinica,2008,37(3):391-393.
[4] 黄先锋.利用机载LIDAR数据重建3D建筑物模型的关键技术研究[D].武汉:武汉大学,2006.
Huang X F.Research on 3D Building Model Extraction from Airborne LIDAR Data[D].Wuhan:Wuhan University,2006.
[5] 张小红,耿江辉.用不变矩从机载激光扫描测高点云数据中重建规则房屋[J].武汉大学学报(信息科学版),2006,31(2):168-171.
Zhang X H,Geng J H.Building reconstruction from airborne laser altimetry points cloud data set based on invariant moments[J].Geomatics and Information Science of Wuhan University,2006,31(2):168-171.
[6] Awwad T M,Zhu Q,Du Z Q,et al.An improved segmentation approach for planar surfaces from unstructured 3D point clouds[J].The Photogrammetric Record,2010,25(129):5-23.
[7] Boulaassal H,Landes T,Grussenmeyer P,et al.Automatic segmentation of building facades using terrestrial laser data[C]//ISPRS workshop on laser scanning and silvilaser.Espoo,Finland:ISPRS,2007:65-70.
[8] Besl P J,Jain R C.Segmentation through variable-order surface fitting[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1988,10(2):167-192.a
[9] Vosselman G,Gorte B G H,Sithole G,et al.Recognising structure in laser scanner point clouds[J].International Archives of Photogrammetry,Remote Sensing and Spatial Information Sciences,2004,46(8):33-38.
[10] Biosca J,Lerma J L.Unsupervised robust planar segmentation of terrestrial laser scanner point clouds based on fuzzy clustering methods[J].ISPRS Journal of Photogrammetry and Remote Sensing,2008,63(1):84-98.
[11] Gorte B.Segmentation of TIN-structured surface models[C]//Proceedings Joint International Symposium on Geospatial Theory Processing and Application.Ottawa,Canada:ISPRS,2002:465-469.
[12] Tóvári D,Pfeifer N.Segmentation based robust interpolation-a new approach to laser data filtering[C]//ISPRS WG III/3,III/4,V/3 Workshop “Laser scanning 2005”.Enschede,the Netherlands:ISPRS,2005:79-84.
[13] Rabbani T,Van den Heuvel F,Vosselman G.Segmentation of point clouds using smoothness constraint[C]//ISPRS Commission V Symposium “Image Engineering and Vision Metrology”.Dresden,German:ISPRS,2006:248-253.
[14] Pu S,Vosselman G.Automatic extraction of building features from terrestrial laser scanning[C]//ISPRS Commission V Symposium “Image Engineering and Vision Metrology”,Dresden,German:ISPRS,2006:25-27.
[15] Filin S.Surface clustering from airborne laser scanning data[C]//ISPRS Commission III Symposium “Photogrammetric Computer Vision”.Graz,Austria:ISPRS,2002:119-124.
[16] Hofmann A D,Maas H G,Streilein A.Derivation of roof types by cluster analysis in parameter spaces of airborne laserscanner point clouds[C]//IAPRS International Archives of Photogrammetry and Remote Sensing and Spatial Information Sciences.Dresden,Germany:IAPRS,2003,34:112-117.
[17] Hough P V C.Method and Means for Recognizing Complex Patterns:U.S.,Patent 3.069.654[P].1962-12-18.
[18] 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.
[19] Tarsha-Kurdi F,Landes T,Grussenmeyer P.Hough-transform and extended ransac algorithms for automatic detection of 3D building roof planes from lidar data[C]//ISPRS Workshop on Laser Scanning and SilviLaser.Espoo,Finland:ISPRS,2007:407-412.
[20] Schnabel R,Wahl R,Klein R.Efficient RANSAC for point-cloud shape detection[J].Computer Graphics Forum,2007,26(2):214-226.
2017, Vol. 29 
