Integrated utilization of images and LiDAR point clouds for damage scale estimation and Identification of bridge component
##article.authors##
- Takumi Sasaki Graduate School of Engineering, University of Tokyo
- Kenta Itakura ImVisionLabs Inc.
-
Pang-jo CHUN
Graduate School of Engineering, University of Tokyo
https://researchmap.jp/p_chun
DOI:
https://doi.org/10.51094/jxiv.1276Keywords:
Deep Learning, Crack Segmentation, Segment Anything Model, Sensor Fusion Point CloudAbstract
In this study， we propose a method for detecting cracks and extracting damage information by integrating point cloud data with corresponding images， aiming to enhance the efficiency of inspection and maintenance of aging bridge structures. To improve detection accuracy， the Segment Anything Model (SAM) was employed as a supplemental segmentation tool. Image-based crack detection was performed using deep learning， and the results were projected onto the point cloud data through geometric calibration. Utilizing the spatial resolution of the point cloud， the length of each detected crack was quantitatively estimated. The proposed framework enables accurate damage assessment and offers practical potential for automating bridge inspection tasks.
Conflicts of Interest Disclosure
No potential conflicts of interest were disclosed.Downloads *Displays the aggregated results up to the previous day.
References
国土交通省:老朽化の現状・老朽化対策の課題， https://www.mlit.go.jp/road/content/001574275.pdf (Retrieved on March 31, 2025)
国土交通省:老朽化対策の本格実施について， https://www.mlit.go.jp/common/001027125.pdf (Retrieved on March 31, 2025)
Hattori, K., Oki, K., Sugita, A., Sugiyama, T., and Chun， P.J. : Deep learning-based corrosion inspection of long- span bridges with BIM integration, Heliyon, Vol.10, No.15, 2024.
Yamane, T., Chun, P.J., and Honda, R. : Detecting and localizing damage based on image recognition and structure from motion, and reflecting it in a 3D bridge model, Structure and Infrastructure Engineering, Vol.20, No.4, 594-606, 2024.
杉本直也, : デジタルツインによる未来の「まち」づ くり ~VIRTUAL SHIZUOKA 構想~, AI・データサ イエンス論文集, 4 巻 2 号, pp.97-101, 2023.
東京都 : 東京都デジタルツイン実現プロジェクト, : https://info.tokyo-digitaltwin.metro.tokyo.lg.jp/ (Retrieved on March 31, 2025)
Abe, M., Sugisaki, K., and Chun, P.J. : Artificial intelligence in infrastructure management, Intelligence， Informatics and Infrastructure, Vol.5, No.2，pp.95-105, 2024.
日高菜緒:点群データ処理アルゴリズムの総括およ び土木分野での活用事例と展望, AI・データサイエ ンス論文集, 4 巻 3 号, pp.301-109, 2023.
中村健二, 今井龍一, 塚田義典, 梅原喜政, 田中成典 : 点群データを用いたプロダクトモデルの実装に関す る研究- Semantic Point Cloud Data -, AI・データサ イエンス論文集, 3 巻 J2 号, pp.870-878, 2022.
田中成典, 今井龍一, 中村健二, 川野浩平 : 点群座標デ ータを用いた 3 次元モデルの生成に関する研究, 知能 と情報, 23 巻 4 号, pp.572-590, 2011.
稲富翔伍, 全邦釘 : 点群の画像化とディープラーニン グを用いた橋梁点群のセグメンテーション, AI・デ ータサイエンス論文集, 2 巻 J2 号, pp.418-427, 2021.
関和彦, 山口愛加, 窪田諭 : 3 次元点群データを用いた 道路橋の損傷抽出とヒートマップ表示, 土木学会論 文集, Vol.79, No.10, pp.1-10, 2023.
.
板倉健太, 林拓哉, 上脇優人, 全邦釘 : セマンティック セグメンテーションやセンサーフュージョンを利用 した橋梁の構造情報の推定のための点群処理手法の 開発, AI・データサイエンス論文集, 5 巻 3 号, pp.10- 21, 2024.
Bianchi,E., and Hebdon,M. : Development of Extendable Open-Source Structural Inspection Datasets, Journal of Computing in Civil Engineering, Vol.36, No.6, 2022.
Bianchi,E., and Hebdon,M. : Concrete Crack Conglomerate Dataset, University Libraries, Virginia Tech， 2021.
Bianchi,E., and Hebdon,M. : Labeled Cracks in the Wild (LCW) Dataset, University Libraries, Virginia Tech， 2021.
Lin, C., Abe, S., Zheng, S., Li, X., and Chun,P.J. : A structure‐oriented loss function for automated semantic segmentation of bridge point clouds, Computer‐Aided Civil and Infrastructure Engineering, V.40, No.6, pp.801- 816, 2025.
Kirillov, A., Mintun, E., Ravi, N., Mao,H., Rolland,C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A.C., Lo, W.Y., Dollár, P. , and Girshick, R. : Segment Anything arXiv:2304.02643v1, 2023.
Izumi, S., and Chun, P. J. : Low-cost training data creation for crack detection using an attention mechanism in deep learning models. Intelligence ， Informatics and Infrastructure, Vol.5, No.1 , pp.124-134, 2024.
板倉健太, 林拓哉, 上脇優人, 全邦釘 : LiDAR とカメラ のセンサーフュージョンによる点群からのノイズ除 去, AI・データサイエンス論文集, 5 巻 3 号, pp.757- 768, 2024.
板倉健太, 林拓哉, 斎藤嘉人, 全邦釘 : センサーフュー ジョンを利用した 3 次元点群からの錆の検出, Jxiv, doi: https://doi.org/10.51094/jxiv.1160
Matterport.Inc., : Matterport Pro3 技 術 仕 様 https://support.matterport.com/s/article/Pro3-Technical- Specifications?language=ja (Retrieved on March 31, 2025)
Chun, P. J., and Kikuta,T. : Self‐training with Bayesian neural networks and spatial priors for unsupervised domain adaptation in crack segmentation, Computer‐Aided Civil and Infrastructure Engineering, Vol.39, No.17, pp.2642- 2661, 2025.
Deng, L., Yuan, H., Long, L., Chun, P.J., Chen, W., and Chu, H. : Cascade refinement extraction network with active boundary loss for segmentation of concrete cracks from high-resolution images. Automation in Construction, Vol. 162, 105410, 2024.
Downloads
Posted
Submitted: 2025-05-27 10:22:31 UTC
Published: 2025-06-03 08:05:07 UTC
License
Copyright (c) 2025
Takumi Sasaki
Kenta Itakura
Pang-jo CHUN
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
