Building facade window model construction of vehicle point cloud data

doi:10.13474/j.cnki.11-2246.2020.0153

Abstract

Abstract: Using vehicle LiDAR data to build window model is a hard work. First, the RANSAC algorithm is used to detect and separate the main wall of the building facade, and the Windows on the main wall are clustered based on empty ideas. Then, the dynamic elliptic convex hull algorithm is used to detect the boundary contour points of windows. The obtained window boundary points are segmented by RANSAC algorithm, and the linear fitting and corner point restoration are carried out by using the robust global least squares algorithm. Finally, the window model construction is completed by combining the geometric features of the Windows. The experimental results show that this method can accurately and effectively construct window models in building facades.

Key words: vehicle LiDAR, building façade, RANSAC, clustering segmentation, model building

CLC Number:

P228

FAN Huilong, LI Yongqiang, YANG Qingke, LI Pengpeng, LIU Yakun, ZHAO Shangbin. Building facade window model construction of vehicle point cloud data[J]. Bulletin of Surveying and Mapping, 2020, 0(5): 95-100.

References

[1] BOULAASSAL H,LANDES T,GRUSSENMEYE-R P,et al.Automatic extraction of planar clusters and their contours on building facades recorded by terrestrial laser scanner[J].International Journal of Architectural Computing,2009,7(1):1-20.
[2] 魏征.车载LiDAR点云中建筑物的自动识别与立面几何重建[D].武汉:武汉大学,2012.
[3] 朱园媛,朱庆,张叶廷,等.侧视地图中建筑物轮廓线提取的三维城市模型法[J].测绘学报, 2015,44(9):1036-1041.
[4] 杜建丽,陈动,张振鑫,等.建筑点云几何模型重建方法研究进展[J].遥感学报,2019,23(3):374-391.
[5] ALI H,AHMED B,PAAR G.Robust window detection from 3D laser scanner data[C]//Congress on Image & Signal Processing.[S.l.]:IEEE, 2008.
[6] PU S,VOSSELMAN G.Extracting windows from terrestrial laser scanning[J]. International Archives of Photogram-metry, Remote Sensing and Spatial Information Sciences, 2007,36:3-52.
[7] LLER P, ZENG G, WONKA P, et al. Image-based procedural modeling of facades[J]. Acm Transactions on Graphics, 2007, 26(3):85.
[8] 刘亚文,覃苏舜.点云数据稀疏区域建筑物立面重建方法[J].应用科学学报,2017,35(2):217-225.
[9] 张瑞菊,郑少开,尹建英.建筑物立面点云语义分割方法研究[J].城市勘测,2017(5):22-25.
[10] 杨洋,马一薇,杨靖宇.基于车载激光扫描数据的窗户提取与重建技术[J].海洋测绘,2010,30(3):48-51.
[11] FISCHLER M A, BOLLES R C. Random sampleconsensus:a paradigm for model fitting with applicatiations to image analysis and automated cartography[J].Graphics and Image Processing,1981,24(6):381-395.
[12] 张志佳,魏信,周自强,等.一种基于八邻域深度差的点云边缘提取算法[J].仪器仪表学报,2017,38(8):2015-2021.
[13] 屈亚运,程英蕾,邱浪波.改进的八邻域搜索提取建筑物立体特征方法[J].空军工程大学学报(自然科学版),2015,16(4):66-69.
[14] 杨清科,李永强,范辉龙,等.基于动态椭圆的LiDAR数据窗户边界提取研究[J].地理与地理信息科学,2019,35(2):61-67.
[15] 官云兰,周世健,张立亭,等.稳健整体最小二乘直线拟合[J].工程勘察,2012(2):60-62.