ITSC 2024 Paper Abstract

Close

Paper ThBT13.9

ZHANG, Shirui (SNCF), NICODEME, Claire (SNCF), LEROMANCER, Briac (SNCF)

Computer Vision-Based Method for Digital Twin Modelling in Railway

Scheduled for presentation during the Poster Session "Railway systems and applications" (ThBT13), Thursday, September 26, 2024, 14:30−16:30, Foyer

2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), September 24- 27, 2024, Edmonton, Canada

This information is tentative and subject to change. Compiled on October 7, 2024

Keywords Sensing, Vision, and Perception, Simulation and Modeling

Abstract

Efficient maintenance requires knowledge and expertise about the equipment. This is especially true for public transportation and railway, where security is one of the most important pillars. However, trains and related systems are complex, making expertise difficult to acquire. In addition, given the long lifecycle of railway equipment and infrastructures, some may no longer be documented. Yet, retrieving essential information with the required details is needed. To provide the necessary data, the authors present a novel digital twin-based concept for advanced real-world information gathering. Different modelling techniques such as LiDAR Scanning, RGB-D Scanning and Deep Learning-based scene reconstruction are investigated to create texture-aware 3D models of different railway objects. Representation quality, scale adaptation and access to technologies are discussed. From this perspective, these models are promising for object recognition, predictive maintenance, extended reality (XR) tools development and agents training in Intelligent Transportation Systems (ITS).

 

 

All Content © PaperCept, Inc.


This site is protected by copyright and trademark laws under US and International law.
All rights reserved. © 2002-2024 PaperCept, Inc.
Page generated 2024-10-07  23:49:48 PST  Terms of use