Building roof point extraction based on airborne LiDAR data

doi:10.7523/j.issn.2095-6134.2016.04.015

Abstract

Abstract:

Airborne LiDAR technology is an effective method for obtaining three-dimensional spatial data of buildings with high point density and accuracy, and building roof point cloud extraction is a key process in three-dimensional digital reconstruction.This study proposes a gradually advanced method to extract building roof points.Firstly, most of vegetation points and building wall points are removed by using multiple echo and normal characteristics, which are based on filtering results.Secondly, the remaining points are segmented into clusters by using Euclidean clustering method.Finally, by combining with a digital terrain model (DTM), the points on building roofs are isolated using the building area and height characteristics.The results show that the proposed method extracts roof points based on raw LiDAR data efficiently.

Key words: airborne LiDAR, point cloud, filter, building, roof point extraction

CLC Number:

TP751

LI Liang, WANG Cheng, LI Shihua, XI Xiaohuan. Building roof point extraction based on airborne LiDAR data[J]. , 2016, 33(4): 537-541.

References

[1] 郝明, 史文中, 张华.一种基于LiDAR数据的建筑物自动提取方法[J].测绘通报, 2014(4): 82-85.
[2] Rottensteiner F.A new method for building extraction in urban areas from high-resolution LiDAR data[J].International Archives of Photogrammetry Remote Sensing and Spatial Information Sciences, 2002, 34(3/A): 295-301.
[3] Sun S, Member S, Salvaggio C.Aerial 3D building detection and modeling from airborne LiDAR point clouds[J].IEEE Journal of Selected Topics in Applied Earth Observations & Remote Sensing, 2013, 6(3): 1 440-1 449.
[4] Awrangjeb M, Fraser C.Automatic segmentation of raw LiDAR data for extraction of building roofs[J].Remote Sensing, 2014, 6(5): 3 716-3 751.
[5] Richter R, Döllner M B J.Object class segmentation of massive 3D point clouds of urban areas using point cloud topology[J].International Journal of Remote Sensing, 2013, 34(23):8 408-8 424.
[6] Zhang W, Wang H, Chen Y, et al.3D building roof modeling by optimizing primitive's parameters using constraints from LiDAR data and aerial imagery[J].Remote Sensing, 2014, 6(9):8 107-8 133.
[7] Zhang J, Lin X, Ning X.SVM-based classification of segmented airborne LiDAR point clouds in urban areas[J].Remote Sensing, 2013, 5(8):3 749-3 775.
[8] Zhang K Q, Cjen S, Whiteman D, et al.A progressive morphological filter for removing nonground measurements from airborne LiDAR data[J].IEEE Transactions on Geoscience & Remote Sensing, 2003, 41(4): 872-882.
[9] 隋立春, 张熠斌, 柳艳, 等.基于改进的数学形态学算法的LiDAR点云数据滤波[J].测绘学报, 2010, 39(4): 390-396.
[10] Arya S, Mount D M, Netanyhu N S, et al.An optimal algorithm for approximate nearest neighbors searching fixed dimensions[J].Journal of the ACM, 1998, 45(6): 891-923.
[11] 浮丹丹, 周绍光, 徐洋, 等.基于主成分分析的点云平面拟合技术研究[J].测绘工程, 2014, 23(4):20-23.
[12] 余小东, 武莹, 何腊梅.反距离加权网格化插值算法的改进及比较[J].工程地球物理学报, 2013, 10(6):900-904.
[13] Niemeyer J, Rottensteiner F, Soergel U.Classification of urban LiDAR data using conditional random field and random forests //Urban Remote Sensing Event (JURSE), 2013 Joint.Sao Paulo: IEEE, 2013:139-142.

[1]	MENG Xiting, JI Luyan, ZHAO Yongchao, YANG Weitun. Multi-scale large well building object detection based on deep learning [J]. Journal of University of Chinese Academy of Sciences, 2021, 38(6): 800-808.
[2]	LIAO Honghai, HE Wei, LIN Shuiyang. Heart rate evaluation algorithm based on PE-based MEEMD filter in LFMCW radar [J]. Journal of University of Chinese Academy of Sciences, 2021, 38(5): 666-677.
[3]	XI Yanxin, JI Luyan, GENG Xiurui. An algorithm for multi-target detection in multi-temporal remote sensing images [J]. Journal of University of Chinese Academy of Sciences, 2021, 38(4): 503-510.
[4]	XIAO Ya, ZHOU Wei, CUI Jie, LIU Tingting, XIAO Ling. A load forecast method of composite materials based on LSTM network and Kalman filtering [J]. Journal of University of Chinese Academy of Sciences, 2021, 38(3): 374-381.
[5]	SONG Zhihua, CHEN Kunshan, ZENG Jiangyuan, XU Zhen. A new adaptive filter for slow-moving target detection based on FMCW radar [J]. Journal of University of Chinese Academy of Sciences, 2021, 38(3): 382-391.
[6]	LIU Shan, ZHANG Fengli, WEI Shiying, LIU Na, SHAO Yun. SAR image visual optimization and building damage assessment based on polarimetric decomposition combination [J]. , 2020, 37(6): 750-759.
[7]	ZHANG Zhen, HUANG Qiang, SHENG Xianlei, ZHENG Qingrong. First-principle quantum transport simulations of a fully spin-polarized device TiCl₃/RhCl₃/TiCl₃ [J]. , 2020, 37(4): 458-464.
[8]	ZHANG Zhihui, FENG Yingbin, LI Zhigang, ZHAO Xiaohu. An underwater mining navigation method based on an improved particle filter [J]. , 2020, 37(4): 507-515.
[9]	HU Liang, XIAO Jun, WANG Ying. A vegetation filtering method for rock mass point clouds based on multi-dimensionality features and MLP [J]. , 2020, 37(3): 345-351.
[10]	WANG Shuai, QIN Yuchu, YANG Fukun. Validation for building density remote sensing products of built-up areas at large scale [J]. , 2020, 37(1): 83-92.
[11]	LI Yingrui, XU Jing, LIU Xiang, YI Huiyue. TMRC-Filter: a subband filter design method for Filtered OFDM system [J]. , 2020, 37(1): 120-127.
[12]	MA Xiaoxiao, CHENG Bo, LIU Yueming, CUI Shiai, LIANG Chenbin. PolSAR remote sensing image method for building extraction based on polarization and texture characteristics [J]. , 2019, 36(5): 682-693.
[13]	WANG Feipeng, XIAO Jun, WANG Ying, WANG Yunbiao. An improved ICP method using Gaussian curvature [J]. , 2019, 36(5): 702-708.
[14]	JIA Yingyu, LIU Shibin, DUAN Jianbo, XIE Shuai. Crowdsourcing assessment model combined with quality control for collapsed buildings after the earthquake [J]. , 2019, 36(3): 354-362.
[15]	WANG Pu, XING Yanqiu, WANG Cheng, XI Xiaohuan. A graph cut-based approach for individual tree detection using airborne LiDAR data [J]. , 2019, 36(3): 385-391.