Extracting accurate building outlines from 3D point clouds considering local features

doi:10.13474/j.cnki.11-2246.2023.0231

Abstract

Abstract: Buildings are an important component of cities, and extracting building features from 3D point clouds data in a refined manner is currently a research hotspot. The paper proposes a methods for accurately extracting building outlines from 3D point clouds that considers local features. Firstly, a statistical-based filtering pre-processing method is used to separate ground points and non-ground points, remove outliers, and reduce the number of point clouds. Secondly, a building facade extraction method based on an improved 3D Hough transform is used to extract multiple facades of the point cloud data to improve the accuracy and efficiency of facade extraction. Finally, a point cloud outlines extraction method based on dimensionality reduction boundary indexing to obtain both local features and external outline features. The results demonstrate that our methods can effectively and accurately extract building outlines by fully considering both the overall external contours and local detailed features of the buildings. This methods provides technical support for various applications, such as urban planning and urban renewal.

Key words: local features, improved 3D Hough transformation algorithm, α-shape algorithm, refinement

CLC Number:

P237

XU Jinfang, LUO Xiaolong, JIANG Weidong, ZHONG Kang, RAN Xingxing, LI Bingyang. Extracting accurate building outlines from 3D point clouds considering local features[J]. Bulletin of Surveying and Mapping, 2023, 0(8): 51-56.

References

[1] 王珍,张涛,丁乐乐,等. 融合高度和光谱信息的倾斜摄影数据建筑物自动提取[J]. 测绘通报,2022(2):10-15.
[2] 朱依民,田林亚,毕继鑫,等. 基于机载LiDAR数据的建筑物轮廓提取[J]. 测绘通报,2019(12):65-70.
[3] BALALI V,JAHANGIRI A,MACHIANI S G. Multi-class US traffic signs 3D recognition and localization via image-based point cloud model using color candidate extraction and texture-based recognition[J]. Advanced Engineering Informatics,2017,32:263-274.
[4] WEBER C,HAHMANN S,HAGEN H. Sharp feature detection in point clouds[C]//Proceedings of 2010 Shape Modeling International Conference. Aix-en-Provence,France:IEEE,2010:175-186.
[5] XIA Shaobo,WANG Ruisheng. A fast edge extraction method for mobile lidar point clouds[J]. IEEE Geoscience and Remote Sensing Letters,2017,14(8):1288-1292.
[6] CHEN Xijiang,YU Kegen. Feature line generation and regularization from point clouds[J]. IEEE Transactions on Geoscience and Remote Sensing,2019,57(12):9779-9790.
[7] HACKEL T,WEGNER J D,SCHINDLER K. Contour detection in unstructured 3D point clouds[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas:IEEE,2016:1610-1618.
[8] ZHANG Weini,CHEN Linwei,XIONG Zhangyue,et al. Large-scale point cloud contour extraction via 3D guided multi-conditional generative adversarial network[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2020,164:97-105.
[9] LIU Yujia,D'ARONCO S,SCHINDLER K,et al. PC2WF:3D wireframe reconstruction from raw point clouds[EB/OL].[2022-09-26]. https://arxiv.org/abs/2103.02766.
[10] YU Lequan,LI Xianzhi,FU C W,et al. EC-net:an edge-aware point set consolidation network[C]//Proceedings of 2018 European Conference on Computer Vision. Cham:Springer International Publishing,2018:398-414.
[11] ZHANG Yang,LIU Zhen,LIU Tianpeng,et al. Large-scale point cloud contour extraction via 3D-guided multiconditional residual generative adversarial network[J]. IEEE Geoscience and Remote Sensing Letters,2020,17(1):142-146.
[12] LIN Yangbin,WANG Cheng,CHENG Jun,et al. Line segment extraction for large scale unorganized point clouds[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2015,102:172-183.
[13] TIAN Pengju,HUA Xianghong,TAO Wuyong,et al. Robust extraction of 3D line segment features from unorganized building point clouds[J]. Remote Sensing,2022,14(14):3279.
[14] YU Bing,HU Jinlong,DONG Xiujun,et al. A robust automatic method to extract building facade maps from 3D point cloud data[J]. Remote Sensing,2022,14(16):3848.
[15] LU Xiaohu,LIU Yahui,LI Kai. Fast 3D line segment detection from unorganized point cloud[EB/OL].[2022-09-26]. https://arxiv.org/abs/1901.02532.
[16] VALLET B,BRÉDIF M,SERNA A,et al. TerraMobilita/iQmulus urban point cloud analysis benchmark[J]. Computers & Graphics,2015,49:126-133.
[17] BALLARD D H. Generalizing the Hough transform to detect arbitrary shapes[J]. Pattern Recognition,1981,13(2):111-122.
[18] EDELSBRUNNER H,KIRKPATRICK D,SEIDEL R. On the shape of a set of points in the plane[J]. IEEE Transactions on Information Theory,1983,29(4):551-559.