Parametric modeling and deformation identification of highway guardrail driven by MLS point clouds

doi:10.11947/j.AGCS.2025.20240359

Abstract

Abstract:

Guardrails are critical component of highway infrastructure, and their deformation can significantly impair their protective function. Existing methods for detecting guardrail deformation primarily focus on extracting and modeling guardrails from mobile mapping point clouds. However, these methods often lack in-depth semantic feature analysis of the guardrails and fail to accurately reflect the deformation conditions in reverse modeling. To address these limitations, this study proposes a high-precision parametric modeling framework for guardrails driven by mobile laser scanning (MLS) point clouds and guided by building information modeling (BIM). The framework involves: ① Automated extraction and instantiation of guardrail elements from MLS data; ② Solving structural parameters of guardrail using the random sample consensus (RANSAC) algorithm; and ③ Introducing B-spline curve-based parametric modeling of guardrails, creating realistic guardrail models through modular modeling in Dynamo. Moreover, evaluating guardrail deformation mileage using a curvature and vector-constrained trajectory detection mechanism. This approach enhances the precision of component-level guardrail models, providing a safe and efficient solution for maintenance inspection of various guardrail types. Experimental results demonstrate a guardrail recognition accuracy of 98.7% on highway guardrail. All deformed guardrails on the selected test sections were detected, with localization errors less than 2.2 meters, meeting practical inspection requirements and mitigating traffic safety risks associated with guardrail deformation.

Key words: MLS point clouds, highway guardrails, BIM model, deformation detection, parametric modeling function

CLC Number:

P232

Xin JIA, Qing ZHU, Xuming GE, Ruifeng MA, Han HU. Parametric modeling and deformation identification of highway guardrail driven by MLS point clouds[J]. Acta Geodaetica et Cartographica Sinica, 2025, 54(4): 688-701.

Figures/Tables 22

Fig. 1

Fig. 2

Fig. 3

Fig. 4

Fig. 5

Fig. 6

Fig. 7

Fig. 8

Fig. 9

Fig. 10

Tab. 1

Fig. 11

Tab. 2

Fig. 12

Fig. 13

Fig. 14

Tab. 3

Fig. 15

Fig. 16

Fig. 17

Tab. 4

Tab. 5

References 30

[1]	李升甫. 高速公路改扩建多源激光扫描数据集成处理与应用关键技术[J]. 测绘学报, 2023, 52(11): 2013. DOI:. doi: 10.11947/)AGCS.2023.20220487
	LI Shengfu. Multi-source laser scanning data integration processing and application of key technologies for expressway reconstruction and expansion[J]. Acta Geodaetica et Cartographica Sinica, 2023, 52(11): 2013. DOI:. doi: 10.11947/)AGCS.2023.20220487
[2]	王羽尘, 于斌, 陈晓阳, 等. 基于激光雷达点云的道路几何信息提取与数字化建模研究[J]. 中国公路学报, 2023, 36(3): 45-60.
	WANG Yuchen, YU Bin, CHEN Xiaoyang, et al. Extraction and digital modeling of road geometric information using LiDAR data point clouds[J]. China Journal of Highway and Transport, 2023, 36(3): 45-60.
[3]	杜豫川, 刘成龙, 吴荻非, 等. 新一代智慧高速公路系统架构设计[J]. 中国公路学报, 2022, 35(4): 203-214.
	DU Yuchuan, LIU Chenglong, WU Difei, et al. Framework of the new generation of smart highway[J]. China Journal of Highway and Transport, 2022, 35(4): 203-214.
[4]	HUANG Ming, ZHOU Chuanli, HUO Pengpeng, et al. Expressway guardrail extraction and classification based on slice method[J]. Sensors and Materials, 2020, 32(11): 4005.
[5]	RIO J, FERREIRA B, POÇAS-MARTINS J. Expansion of IFC model with structural sensors[J]. Informes de la Construcción, 2013, 65(530): 219-228.
[6]	SOILÁN M, JUSTO A, SÁNCHEZ-RODRÍGUEZ A, et al. 3D point cloud to BIM: semi-automated framework to define IFC alignment entities from MLS-acquired LiDAR data of highway roads[J]. Remote Sensing, 2020, 12(14): 2301.
[7]	ZHOU Yuzhou, HUANG Ronggang, JIANG Tengping, et al. Highway alignments extraction and 3D modeling from airborne laser scanning point clouds[J]. International Journal of Applied Earth Observation and Geoinformation, 2021, 102: 102429.
[8]	SOILÁN M, NÓVOA A, SÁNCHEZ-RODRÍGUEZ A, et al. Fully automated methodology for the delineation of railway lanes and the generation of IFC alignment models using 3D point cloud data[J]. Automation in Construction, 2021, 126: 103684.
[9]	BIANCARDO S A, VISCIONE N, CERBONE A, et al. BIM-based design for road infrastructure: a critical focus on modeling guardrails and retaining walls[J]. Infrastructures, 2020, 5(7): 59.
[10]	朱庆, 张利国, 丁雨淋, 等. 从实景三维建模到数字孪生建模[J]. 测绘学报, 2022, 51(6): 1040-1049. DOI:. doi: 10.11947/j.AGCS.2022.20210640
	ZHU Qing, ZHANG Liguo, DING Yulin, et al. From real 3D modeling to digital twin modeling[J]. Acta Geodaetica et Cartographica Sinica, 2022, 51(6): 1040-1049. DOI:. doi: 10.11947/j.AGCS.2022.20210640
[11]	SOILÁN M, SÁNCHEZ-RODRÍGUEZ A, DEL RÍO-BARRAL P, et al. Review of laser scanning technologies and their applications for road and railway infrastructure monitoring[J]. Infrastructures, 2019, 4(4): 58.
[12]	PUENTE I, GONZÁLEZ-JORGE H, MARTÍNEZ-SÁNCHEZ J, et al. Review of mobile mapping and surveying technologies[J]. Measurement, 2013, 46(7): 2127-2145.
[13]	WILLIAMS K, OLSEN M J, ROE G V, et al. Synthesis of transportation applications of mobile LiDAR[J]. Remote Sensing, 2013, 5(9): 4652-4692.
[14]	MA Lingfei, LI Ying, LI J, et al. Mobile laser scanned point-clouds for road object detection and extraction: a review[J]. Remote Sensing, 2018, 10(10): 1531.
[15]	方莉娜, 沈贵熙, 游志龙, 等. 融合点云和多视图的车载激光点云路侧多目标识别[J]. 测绘学报, 2021, 50(11): 1558-1573. DOI:. doi: 10.11947/j.AGCS.2021.20210246
	FANG Lina, SHEN Guixi, YOU Zhilong, et al. A joint network of point cloud and multiple views for roadside objects recognition from mobile laser point clouds[J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(11): 1558-1573. DOI:. doi: 10.11947/j.AGCS.2021.20210246
[16]	ZEYBEK M. Extraction of road lane markings from mobile LiDAR data[J]. Transportation Research Record: Journal of the Transportation Research Board, 2021, 2675(5): 30-47.
[17]	PǍTRǍUCEAN V, ARMENI I, NAHANGI M, et al. State of research in automatic as-built modelling[J]. Advanced Engineering Informatics, 2015, 29(2): 162-171.
[18]	BARAZZETTI L, PREVITALI M, SCAIONI M. Roads detection and parametrization in integrated BIM-GIS using LiDAR[J]. Infrastructures, 2020, 5(7): 55.
[19]	NOVÁČEK J, KOHOUT T, VRTAL P, et al. Application of RSA principles to improve the BIM in the road design process with focus on the road restraint systems[J]. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2022, 46: 159-164.
[20]	JUSTO A, SOILÁN M, SÁNCHEZ-RODRÍGUEZ A, et al. Scan-to-BIM for the infrastructure domain: generation of IFC-compliant models of road infrastructure assets and semantics using 3D point cloud data[J]. Automation in Construction, 2021, 127: 103703.
[21]	ZHU Hao, GUO Bin. A beam guardrail detection algorithm using LiDAR for intelligent vehicle[C]//Proceedings of 2018 Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems. Tianjin: IEEE, 2018: 1398-1402.
[22]	JIANG Yu, HE Bei, LIU Li, et al. Effective and robust corrugated beam guardrail detection based on mobile laser scanning data[C]//Proceedings of 2016 International Conference on Intelligent Transportation Systems. Rio de Janeiro: IEEE, 2016: 1540-1545.
[23]	YUE Yuanwen, GOUDA M, EL-BASYOUNY K. Automatic detection and mapping of highway guardrails from mobile LiDAR point clouds[C]//Proceedings of 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS. Brussels: IEEE, 2021: 2520-2523.
[24]	GAO Jianlan, CHEN Yiping, JUNIOR J M, et al. Rapid extraction of urban road guardrails from mobile LiDAR point clouds[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(2): 1572-1577.
[25]	HU Qingyong, YANG Bo, XIE Linhai, et al. RandLA-Net: efficient semantic segmentation of large-scale point clouds[C]//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 11108-11117.
[26]	JIA Xin, ZHU Qing, GE Xuming, et al. Robust guardrail instantiation and trajectory optimization of complex highways based on mobile laser scanning point clouds[J]. Photogrammetric Engineering & Remote Sensing, 2023, 89(3): 151-161.
[27]	KEDZIERSKI M, FRYSKOWSKA A. Terrestrial and aerial laser scanning data integration using wavelet analysis for the purpose of 3D building modeling[J]. Sensors, 2014, 14(7): 12070-12092.
[28]	MA Lingfei, LI Ying, LI J, et al. Generation of horizontally curved driving lines in HD maps using mobile laser scanning point clouds[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2019, 12(5): 1572-1586.
[29]	ZHANG Xiaopeng, LI Hongjun, CHENG Zhanglin. Curvature estimation of 3D point cloud surfaces through the fitting of normal section curvatures[EB/OL]. [2024-06-21]. https://nlpr.ia.ac.cn/2008papers/gjhy/gh129.pdf.
[30]	李振宇, 李林, 朱晓峰, 等. 基于双目视觉的形变护栏检测及里程定位[J]. 交通科技与经济, 2022, 24(2): 24-33.
	LI Zhenyu, LI Lin, ZHU Xiaofeng, et al. Deformation guardrail detection and mileage location based on binocular vision[J]. Technology & Economy in Areas of Communications, 2022, 24(2): 24-33.

方法	聚类数量
方法	直线段	弯道
DBSCAN	6	9
本文方法	3	3
真实值	3	3

试验段	真正例和假负例	真正例和假正例	真正例	精确率/（%）	召回率/（%）
直线	302 869	302 258	299 235	99.0	98.8
弯道	370 246	369 492	363 211	98.4	98.1

类型	已知参数	未知参数
dual-wave	H，L，r₁，r₂，r₃，x₂，x₃，…，x₁₄	Length，R，Position_dual
three-wave	H，L，r₁，r₂，r₃，r₄，r₅，x₂，x₃，…，x₂₀	Length，R，Position_three
pillar	w_post，h_post	Spacing_pillar，Position_pillar，offset，R
anti-dazzle board	Rectangle，Cylinder	Spacing_board，Position_board，offset，R
concrete barriers	trapezoid	Length，Position_barriers

护栏	变形里程检测/m	实际里程位置/m	实际里程范围/m	里程误差/m
1	K46+419.9	K11+422.0	K46+420—K46+430	+2.1
2	K47+457.8	K47+459.1	K47+455—K47+465	+1.3
3	K49+263.0	K49+263.0	K49+270—K49+270	0
4	K49+658.5	K49+659.2	K49+655—K49+665	+0.7
5	K50+341.6	K50+339.1	K50+335—K50+345	－1.5
6	K50+773.4	K50+771.7	K50+765—K50+775	－1.7
7	K51+583.5	K51+585.1	K51+580—K50+590	+1.6
8	K52+766.3	K52+764.8	K52+760—K52+770	－1.5
9	K52+844.7	K52+846.4	K52+840—K52+850	+1.7
10	K54+189.1	K54+190.3	K54+185—K54+195	+1.2
11	K55+380.2	K55+379.0	K55+375—K55+385	－0.8
12	K56+612.3	K56+614.1	K56+610—K56+620	+1.8
13	K57+296.7	K57+298.0	K57+290—K57+230	+1.3
14	K58+146.8	K58+144.6	K58+140—K58+150	－2.2
15	K58+475.0	K58+473.6	K58+470—K58+480	－1.4
16	K59+223.7	K59+224.9	K59+220—K59+230	+1.2

方法	试验路段长度/km	识别精度/（%）	里程定位误差/m	形变护栏数	有效检测数
文献[30]	12	92.8	10.0	11	10
本文方法	15.5	98.7	2.2	16	16