A Method of Extracting Building Roof Edge Points from Airborne Point Clouds with Wide-Area Feature Optimization

HUO Pengpeng; JIANG Jinguang; DONG Youqiang; FAN Hongchao

doi:10.13203/j.whugis20250033

您当前的位置：

首页 >

文章列表页 >

A Method of Extracting Building Roof Edge Points from Airborne Point Clouds with Wide-Area Feature Optimization

Photogrammetry and Remote Sensing | 更新时间：2026-11-05

- A Method of Extracting Building Roof Edge Points from Airborne Point Clouds with Wide-Area Feature Optimization
- Geomatics and Information Science of Wuhan University Vol. 51, Issue 6, Pages: 1216-1227(2026)
- 作者机构：
  
  1.武汉大学卫星导航定位技术研究中心，湖北武汉，430079
  2.武汉大学电子信息学院，湖北武汉，430079
  3.北京市测绘设计研究院，北京，100045
  4.北京建筑大学测绘与城市空间信息学院，北京，102612
  5.挪威科技大学土木与环境系，挪威;特隆赫姆，7034
- 作者简介：
- 基金信息：
- DOI：10.13203/j.whugis20250033
  CLC： P237
- Received：30 June 2025，
  
  Published：05 June 2026
- 稿件说明：
移动端阅览
霍芃芃,江金光,董友强，等.广域特征优化的机载点云建筑屋顶边缘点提取方法[J].武汉大学学报（信息科学版）,2026,51(6):1216-1227.

HUO Pengpeng,JIANG Jinguang,DONG Youqiang,et al.A Method of Extracting Building Roof Edge Points from Airborne Point Clouds with Wide-Area Feature Optimization[J].Geomatics and Information Science of Wuhan University,2026,51(6):1216-1227.
霍芃芃,江金光,董友强，等.广域特征优化的机载点云建筑屋顶边缘点提取方法[J].武汉大学学报（信息科学版）,2026,51(6):1216-1227. DOI：10.13203/j.whugis20250033

HUO Pengpeng,JIANG Jinguang,DONG Youqiang,et al.A Method of Extracting Building Roof Edge Points from Airborne Point Clouds with Wide-Area Feature Optimization[J].Geomatics and Information Science of Wuhan University,2026,51(6):1216-1227. DOI：10.13203/j.whugis20250033

摘要

机载点云是建筑屋顶边缘点提取的关键数据源，当前提取方法普遍存在自动化程度较低和准确度不足的问题。针对以上问题，提出一种基于机载点云的建筑屋顶边缘点机器学习提取策略，高效集成各类点云边缘点检测特征优势，可实现复杂场景下的自适应建筑屋顶边缘点提取。首先将建筑屋顶点云实施降维处理，生成多级特征并确定尺度不变特征，然后利用多种点云特征检测算法计算建筑屋顶边缘在多尺度下的强区别性特征，形成特征矩阵并输入至CatBoost（categorical boosting）分类模型进行训练与预测，最后实现建筑屋顶边缘点的准确提取。为验证所提方法的有效性，选取挪威特隆赫姆市机载点云数据集进行测试，最终建筑屋顶边缘点的提取准确率可达91.16%，耗时表现良好且平稳。实验结果表明，所提方法仅需少量标注数据即可有效收敛，为建筑屋顶边缘点提取提供了高效、精确且泛化性良好的方案。

Abstract

Objectives

Airborne point cloud serves as a crucial data source for the extraction of building roof edge points. However

current extraction methods generally suffer from low automation levels and insufficient accuracy.

Methods

To address these issues

we innovatively propose a machine-learning-based extraction strategy for building roof edge points from airborne point clouds. The proposed method efficiently integrates the advantages of various point-cloud-based edge-point detection features

enabling the adaptive extraction of building roof edge points in complex scenarios. First

the proposed method performs dimensionality reduction on the point cloud of the building roof

generating multi-level features and determining scale-invariant features. Subsequently

multiple point-cloud feature-detection algorithms are utilized to calculate highly discriminative features of building roof edges at multiple scales. These features form a feature matrix

which is then input into the categorical boosting machine-learning algorithm for training and prediction

ultimately achieving the accurate extraction of building roof edge points.

Results

To verify the proposed method

the airborne point-cloud dataset of Trondheim

Norway is selected for testing. The extraction accuracy of building roof edge points can reach 91.16%

and the time-consuming performance is good and stable.

Conclusions

Experimental results demonstrate that the proposed method can converge effectively with only a small amount of labeled data

providing an efficient

accurate

and highly generalizable solution for the extraction of building roof edge points.

关键词

Keywords

references

GUMHOLD S ， WANG X L ， MACLEOD R . Feature Extraction from Point Clouds ［C］// The 10th International Meshing Roundtable ， Newport Beach， USA ， 2001 .

PAULY M ， GROSS M ， KOBBELT L P . Efficient Simplification of Point-Sampled Surfaces ［C］// IEEE Visualization ， Boston， USA ， 2002 .

RUSU R B ， BLODOW N ， BEETZ M . Fast Point Feature Histograms for 3D Registration ［C］// IEEE International Conference on Robotics and Automation ， Kobe， Japan ， 2009 .

ATTENE M ， FALCIDIENO B ， ROSSIGNAC J ， et al . Sharpen & Bend： Recovering Curved Sharp Edges in Triangle Meshes Produced by Feature-Insensitive Sampling ［J］. IEEE Transactions on Visualization and Computer Graphics ， 2005 ， 11 （ 2 ）： 181 - 192 .

FLEISHMAN S ， COHEN-OR D ， SILVA C T . Robust Moving Least-Squares Fitting with Sharp Features ［J］. ACM Transactions on Graphics ， 2005 ， 24 （ 3 ）： 544 - 552 .

DANIELS II J ， OCHOTTA T ， HA L K ， et al . Spline-Based Feature Curves from Point-Sampled Geometry ［J］. The Visual Computer ， 2008 ， 24 （ 6 ）： 449 - 462 .

NI H ， LIN X G ， NING X G ， et al . Edge Detection and Feature Line Tracing in 3D-Point Clouds by Analyzing Geometric Properties of Neighborhoods ［J］. Remote Sensing ， 2016 ， 8 （ 9 ）： 710 .

MITROPOULOU A ， GEORGOPOULOS A . An Automated Process to Detect Edges in Unorganized Point Clouds ［J］. ISPRS Annals of the Photogrammetry， Remote Sensing and Spatial Information Sciences ， 2019 ， IV-2/W 6 ： 99 - 105 .

马天恩，刘涛，杜萍，等 . 一种聚合全局上下文信息的三维点云语义分割方法［J］. 武汉大学学报（信息科学版）， 2025 ， 50 （ 12 ）： 2548 - 2559 .

MA Tianen ， LIU Tao ， DU Ping ， et al . A 3D Point Cloud Semantic Segmentation Method for Aggregating Global Context Information ［J］. Geomatics and Information Science of Wuhan University ， 2025 ， 50 （ 12 ）： 2548 - 2559 .

汤圣君，张韵婕，李晓明，等 . 超体素随机森林与LSTM神经网络联合优化的室内点云高精度分类方法［J］. 武汉大学学报（信息科学版）， 2023 ， 48 （ 4 ）： 525 - 533 .

TANG Shengjun ， ZHANG Yunjie ， LI Xiaoming ， et al . A High-Precision Indoor Point Cloud Classification Method Jointly Optimized by Super Voxel Random Forest and LSTM Neural Network ［J］. Geomatics and Information Science of Wuhan University ， 2023 ， 48 （ 4 ）： 525 - 533 .

FAN H . TBA 4256 3D Digital Modelling： Segmentation［EB/OL］. ［ 2026-04-18 ］. https：//ntnu.blackboard.com/ https://ntnu.blackboard.com/ .

RYDE J ， DELMERICO J A . Extracting Edge Voxels from 3D Volumetric Maps to Reduce Map Size and Accelerate Mapping Alignment ［C］// The 9th Conference on Computer and Robot Vision ， Toronto， Canada ， 2012 .

BORRMANN D ， ARZBERGER F ， JÖRISSEN S . Robotic 3D Scan Repository ［EB/OL］. ［ 2026-04-18 ］. http：//kos.informatik.uni-osnabrueck.de/3Dscans/ http://kos.informatik.uni-osnabrueck.de/3Dscans/ .

WEBER C ， HAHMANN S ， HAGEN H . Sharp Feature Detection in Point Clouds ［C］// Shape Modeling International Conference ， Aix-en-Provence， France ， 2010 .

CHARLES R Q ， HAO S ， MO K C ， et al . PointNet： Deep Learning on Point Sets for 3D Classification and Segmentation ［C］// IEEE Conference on Computer Vision and Pattern Recognition ， Honolulu， USA ， 2017 .

HACKEL T ， WEGNER J D ， SCHINDLER K . Contour Detection in Unstructured 3D Point Clouds ［C］// IEEE Conference on Computer Vision and Pattern Recognition ， Las Vegas， USA ， 2016 .

HIMEUR C E ， LEJEMBLE T ， PELLEGRINI T ， et al . PCEDNet： A Lightweight Neural Network for Fast and Interactive Edge Detection in 3D Point Clouds ［J］. ACM Transactions on Graphics ， 2021 ， 41 （ 1 ）： 1 - 21 .

DEMANTKÉ J ， MALLET C ， DAVID N ， et al . Dimensionality Based Scale Selection in 3D LiDAR Point Clouds ［J］. Remote Sensing and Spatial Information Sciences ， 2011 ， 38 （ 5 ）： 97 - 102 .

GÜNEN M A . Adaptive Neighborhood Size and Effective Geometric Features Selection for 3D Scattered Point Cloud Classification ［J］. Applied Soft Computing ， 2022 ， 115 ： 108196 .

徐旺，游雄，张威巍，等 . 面向城市增强现实信息标注的建筑物场景结构提取方法［J］. 武汉大学学报（信息科学版）， 2023 ， 48 （ 6 ）： 926 - 935 .

XU Wang ， YOU Xiong ， ZHANG Weiwei ， et al . Building Scene Structure Extraction Method for Urban Augmented Reality Annotation ［J］. Geomatics and Information Science of Wuhan University ， 2023 ， 48 （ 6 ）： 926 - 935 .

HANCOCK J T ， KHOSHGOFTAAR T M . CatBoost for Big Data： An Interdisciplinary Review ［J］. Journal of Big Data ， 2020 ， 7 （ 1 ）： 94 .

BENTÉJAC C ， CSÖRGŐ A ， MARTÍNEZ-MUÑOZ G . A Comparative Analysis of Gradient Boosting Algorithms ［J］. Artificial Intelligence Review ， 2021 ， 54 （ 3 ）： 1937 - 1967 .

DOROGUSH A V ， ERSHOV V ， GULIN A . CatBoost： Gradient Boosting with Categorical Features Support ［EB/OL］. ［ 2025-12-23 ］. https：//arxiv.org/abs/1810.11363 https://arxiv.org/abs/1810.11363 .

龚健雅，张展，贾浩巍，等 . 面向多源数据地物提取的遥感知识感知与多尺度特征融合网络［J］. 武汉大学学报（信息科学版）， 2022 ， 47 （ 10 ）： 1546 - 1554 .

GONG Jianya ， ZHANG Zhan ， JIA Haowei ， et al . Multi-source Data Ground Object Extraction Based on Knowledge-Aware and Multi-scale Feature Fusion Network ［J］. Geomatics and Information Science of Wuhan University ， 2022 ， 47 （ 10 ）： 1546 - 1554 .

MILLMAN K J ， AIVAZIS M . Python for Scientists and Engineers ［J］. Computing in Science & Engineering ， 2011 ， 13 （ 2 ）： 9 - 12 .

ZHOU Q Y ， PARK J ， KOLTUN V . Open 3 D： A Modern Library for 3D Data Processing［EB/OL］. ［ 2026-01-15 ］. https：//arxiv.org/abs/1801.09847 https://arxiv.org/abs/1801.09847 .

WANG H J ， LIANG Q X ， HANCOCK J T ， et al . Feature Selection Strategies： A Comparative Analysis of SHAP-Value and Importance-Based Methods ［J］. Journal of Big Data ， 2024 ， 11 （ 1 ）： 44 .

HARRIS C R ， MILLMAN K J ， VAN DER WALT S J ， et al . Array Programming with NumPy ［J］. Nature ， 2020 ， 585 （ 7825 ）： 357 - 362 .

THE PANDAS DEVELOPMENT TEAM . Pandas-Dev/pandas： Pandas ［EB/OL］. ［ 2026-04-18 ］. https：//doi.org/10.5281/zenodo.3509134 https://doi.org/10.5281/zenodo.3509134 .

ZHANG J Y ， ZHAO X L ， CHEN Z ， et al . A Review of Deep Learning-Based Semantic Segmentation for Point Cloud ［J］. IEEE Access ， 2019 ， 7 ： 179118 - 179133 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Machine Learning-Based Remote Sensing Retrieval of Soil Moisture： Advances and Challenges

Machine Learning Downscaling Methods for Inversion of Terrestrial Water Storage Anomalies in the Yangtze River Basin by GRACE

An Integrated Rule-Based and Machine Learning Method for Trip Purpose Identification

Quantitative Assessment of Natural and Human Activity Impacts on Spatial Network of Urban Thermal Environment in Resource-Depleted City

High-Accuracy Orbit Prediction of Low Earth Orbit Satellites Using Machine Learning Algorithms

Related Author

ZHANG Liangpei

SHEN Huanfeng

LI Jie

YANG Qianqian

LI Zhenghao

YUAN Qiangqiang

LI Qiong

ZHANG Dong

Related Institution

State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University

School of Resources and Environmental Sciences, Wuhan University

Department of Geography, Faculty of Social Sciences, Hong Kong Baptist University

School of Geodesy and Geomatics, Wuhan University

National Gravitation Laboratory, Huazhong University of Science and Technology

AI问答

⁰