Computational Technology Resources - CCC

G. Dufau, J. Sanchez, I. El Ghazaly, G. Neveu, B. Salavati, "3D-to-Plan: Automatic Generation of CAD Sketch of Retaining Walls from Trainborne LiDAR Point Clouds", in J. Pombo, (Editor), "Proceedings of the Seventh International Conference on Railway Technology: Research, Development and Maintenance ", Civil-Comp Press, Edinburgh, UK, Online volume: CCC 15, Paper 8.10, 2026, doi:10.4203/ccc.15.8.10

Keywords: LiDAR, retaining walls, artificial intelligence, CAD, point cloud, segmentation.

Abstract

LiDAR has been growing in railway maintenance operations and has started to become a staple of reliable geometric analysis of railway scenes. Despite this flourishing interest, few methods are published on automatic high-level analysis. In this work, we aim at providing a clear pipeline to showcase the use of trainborne LiDAR data for industrial use and continuous maintenance. More specifically, we propose a method to provide geometry-preserving CAD sketch of retaining walls to alleviate the burden on operation workers needing to freehand draw them. While methods based on photogrammetry or TLS (terrestrial laser scan) exist, they usually require human intervention in the process, whereas in this paper we propose a human-free method from acquisition to result, with a very cost-effective processing time (~15 minutes per retaining walls).

download the full-text of this paper (PDF, 1720 Kb)

go to the previous paper
go to the next paper
return to the table of contents
return to the volume description

	Computational & Technology Resources an online resource for computational, engineering & technology publications
	not logged in - login
Front Page Browse CCC CCP CSETS CTR IJRT Other Authors Search Purchase Guide FAQ Contact us	Civil-Comp Conferences ISSN 2753-3239 CCC: 15 PROCEEDINGS OF THE SEVENTH INTERNATIONAL CONFERENCE ON RAILWAY TECHNOLOGY: RESEARCH, DEVELOPMENT AND MAINTENANCE Edited by: J. Pombo Paper 8.10 3D-to-Plan: Automatic Generation of CAD Sketch of Retaining Walls from Trainborne LiDAR Point Clouds G. Dufau, J. Sanchez, I. El Ghazaly, G. Neveu and B. Salavati , SNCF Réseau, France doi:10.4203/ccc.15.8.10 Full Bibliographic Reference for this paper G. Dufau, J. Sanchez, I. El Ghazaly, G. Neveu, B. Salavati, "3D-to-Plan: Automatic Generation of CAD Sketch of Retaining Walls from Trainborne LiDAR Point Clouds", in J. Pombo, (Editor), "Proceedings of the Seventh International Conference on Railway Technology: Research, Development and Maintenance ", Civil-Comp Press, Edinburgh, UK, Online volume: CCC 15, Paper 8.10, 2026, doi:10.4203/ccc.15.8.10 Keywords: LiDAR, retaining walls, artificial intelligence, CAD, point cloud, segmentation. Abstract LiDAR has been growing in railway maintenance operations and has started to become a staple of reliable geometric analysis of railway scenes. Despite this flourishing interest, few methods are published on automatic high-level analysis. In this work, we aim at providing a clear pipeline to showcase the use of trainborne LiDAR data for industrial use and continuous maintenance. More specifically, we propose a method to provide geometry-preserving CAD sketch of retaining walls to alleviate the burden on operation workers needing to freehand draw them. While methods based on photogrammetry or TLS (terrestrial laser scan) exist, they usually require human intervention in the process, whereas in this paper we propose a human-free method from acquisition to result, with a very cost-effective processing time (~15 minutes per retaining walls). download the full-text of this paper (PDF, 1720 Kb) go to the previous paper go to the next paper return to the table of contents return to the volume description
Back to top	©Civil-Comp Limited 2023 - terms & conditions