Asset Detection in Railroad Environments using Deep Learning-based Scanline Analysis

Johannes Wolf, Rico Richter, Jürgen Döllner

2021

Abstract

This work presents an approach for the automated detection of railroad assets in 3D point clouds from mobile mapping LiDAR scans using established convolutional neural networks for image analysis. It describes how images of individual scan lines can be generated from 3D point clouds. In these scan lines, objects such as tracks, signal posts, and axle counters can be detected using artificial neural networks for image analysis, previously trained on ground-truth data. The recognition results can then be transferred back to the 3D point cloud as a semantic classification result, or they are used to generate geometry or map data for further processing in GIS applications. Using this approach, trained objects can be found with high automation. Challenges such as varying point density, different data characteristics of scanning devices, and the massive amount of data can be overcome with this approach.

Paper Citation

in Harvard Style

Wolf J., Richter R. and Döllner J. (2021). Asset Detection in Railroad Environments using Deep Learning-based Scanline Analysis. In Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 4: VISAPP; ISBN 978-989-758-488-6, SciTePress, pages 465-470. DOI: 10.5220/0010314704650470

in Bibtex Style

@conference{visapp21,
author={Johannes Wolf and Rico Richter and Jürgen Döllner},
title={Asset Detection in Railroad Environments using Deep Learning-based Scanline Analysis},
booktitle={Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 4: VISAPP},
year={2021},
pages={465-470},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010314704650470},
isbn={978-989-758-488-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 4: VISAPP
TI - Asset Detection in Railroad Environments using Deep Learning-based Scanline Analysis
SN - 978-989-758-488-6
AU - Wolf J.
AU - Richter R.
AU - Döllner J.
PY - 2021
SP - 465
EP - 470
DO - 10.5220/0010314704650470
PB - SciTePress