Automated 3D defect inspection in shield tunnel linings through integration of image and point cloud data

Abstract Recent advancements in automated tunnel defect detection have utilized high-resolution cameras and mobile laser scanners. However, the inability of cameras to accurately capture 3D spatial coordinates complicates tasks such as 3D visualization, while the relatively low resolution of laser s...

Full description

Saved in:
Bibliographic Details
Main Authors: Hongwei Huang, Shuyi Liu, Mingliang Zhou, Hua Shao, Qingtong Li, Phromphat Thansirichaisree
Format: Article
Language:English
Published: Springer Nature 2025-05-01
Series:AI in Civil Engineering
Subjects:
Online Access:https://doi.org/10.1007/s43503-025-00054-w
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850278108301623296
author Hongwei Huang
Shuyi Liu
Mingliang Zhou
Hua Shao
Qingtong Li
Phromphat Thansirichaisree
author_facet Hongwei Huang
Shuyi Liu
Mingliang Zhou
Hua Shao
Qingtong Li
Phromphat Thansirichaisree
author_sort Hongwei Huang
collection DOAJ
description Abstract Recent advancements in automated tunnel defect detection have utilized high-resolution cameras and mobile laser scanners. However, the inability of cameras to accurately capture 3D spatial coordinates complicates tasks such as 3D visualization, while the relatively low resolution of laser scanners makes it difficult to detect small defects such as microcracks. In this paper, a comprehensive inspection method is proposed to address these limitations by integrating multi-defect detection, 3D coordinate acquisition, and visualization. The inspection process involves the capture of both image data and point cloud data of tunnel linings using the newly developed inspection cart (MTI-300). The proposed fusion approach combines image and point cloud data, leveraging the enhanced YOLOv8-seg instance segmentation model for defect identification. The scale-invariant feature transform (SIFT) algorithm is used to match local defect regions in the image data with the corresponding point cloud data, enabling the extraction of 3D coordinates and the integration of defect pixels with the point cloud information. Subsequently, a lightweight 3D reconstruction model is developed to visualize the entire tunnel and its defects using the fused data. The performance of the proposed method is validated and substantiated through a field experiment on Metro Line 8 in Qingdao, China.
format Article
id doaj-art-5b983046ff7f420fa553b36ecf0f7f0e
institution OA Journals
issn 2097-0943
2730-5392
language English
publishDate 2025-05-01
publisher Springer Nature
record_format Article
series AI in Civil Engineering
spelling doaj-art-5b983046ff7f420fa553b36ecf0f7f0e2025-08-20T01:49:39ZengSpringer NatureAI in Civil Engineering2097-09432730-53922025-05-014112310.1007/s43503-025-00054-wAutomated 3D defect inspection in shield tunnel linings through integration of image and point cloud dataHongwei Huang0Shuyi Liu1Mingliang Zhou2Hua Shao3Qingtong Li4Phromphat Thansirichaisree5Key Laboratory of Geotechnical and Underground Engineering of Ministry of Education and Department of Geotechnical Engineering, Tongji UniversityKey Laboratory of Geotechnical and Underground Engineering of Ministry of Education and Department of Geotechnical Engineering, Tongji UniversityKey Laboratory of Geotechnical and Underground Engineering of Ministry of Education and Department of Geotechnical Engineering, Tongji UniversityShanghai Metro Maintenance Co., Ltd.Shanghai Shentong Metro Group Co., Ltd.Thammasat School of Engineering, Thammasat University RangsitAbstract Recent advancements in automated tunnel defect detection have utilized high-resolution cameras and mobile laser scanners. However, the inability of cameras to accurately capture 3D spatial coordinates complicates tasks such as 3D visualization, while the relatively low resolution of laser scanners makes it difficult to detect small defects such as microcracks. In this paper, a comprehensive inspection method is proposed to address these limitations by integrating multi-defect detection, 3D coordinate acquisition, and visualization. The inspection process involves the capture of both image data and point cloud data of tunnel linings using the newly developed inspection cart (MTI-300). The proposed fusion approach combines image and point cloud data, leveraging the enhanced YOLOv8-seg instance segmentation model for defect identification. The scale-invariant feature transform (SIFT) algorithm is used to match local defect regions in the image data with the corresponding point cloud data, enabling the extraction of 3D coordinates and the integration of defect pixels with the point cloud information. Subsequently, a lightweight 3D reconstruction model is developed to visualize the entire tunnel and its defects using the fused data. The performance of the proposed method is validated and substantiated through a field experiment on Metro Line 8 in Qingdao, China.https://doi.org/10.1007/s43503-025-00054-wTunnel defectAutomated inspection3D reconstructionImage segmentationPoint cloud
spellingShingle Hongwei Huang
Shuyi Liu
Mingliang Zhou
Hua Shao
Qingtong Li
Phromphat Thansirichaisree
Automated 3D defect inspection in shield tunnel linings through integration of image and point cloud data
AI in Civil Engineering
Tunnel defect
Automated inspection
3D reconstruction
Image segmentation
Point cloud
title Automated 3D defect inspection in shield tunnel linings through integration of image and point cloud data
title_full Automated 3D defect inspection in shield tunnel linings through integration of image and point cloud data
title_fullStr Automated 3D defect inspection in shield tunnel linings through integration of image and point cloud data
title_full_unstemmed Automated 3D defect inspection in shield tunnel linings through integration of image and point cloud data
title_short Automated 3D defect inspection in shield tunnel linings through integration of image and point cloud data
title_sort automated 3d defect inspection in shield tunnel linings through integration of image and point cloud data
topic Tunnel defect
Automated inspection
3D reconstruction
Image segmentation
Point cloud
url https://doi.org/10.1007/s43503-025-00054-w
work_keys_str_mv AT hongweihuang automated3ddefectinspectioninshieldtunnelliningsthroughintegrationofimageandpointclouddata
AT shuyiliu automated3ddefectinspectioninshieldtunnelliningsthroughintegrationofimageandpointclouddata
AT mingliangzhou automated3ddefectinspectioninshieldtunnelliningsthroughintegrationofimageandpointclouddata
AT huashao automated3ddefectinspectioninshieldtunnelliningsthroughintegrationofimageandpointclouddata
AT qingtongli automated3ddefectinspectioninshieldtunnelliningsthroughintegrationofimageandpointclouddata
AT phromphatthansirichaisree automated3ddefectinspectioninshieldtunnelliningsthroughintegrationofimageandpointclouddata