Enhancing Railway Safety: An Unsupervised Approach for Detecting Missing Bolts with Deep Learning and 3D Imaging

Udith Krishnan Vadakkum Vadukkal, Angelo Cardellicchio, Nicola Mosca, Maria di Summa, Massimiliano Nitti, Ettore Stella, Vito Renò

2024

Abstract

This paper delves into the realm of quality control within railway infrastructure, specifically addressing the critical issue of missing bolts. Leveraging 3D imaging and deep learning, the study compares two approaches: a binary classification method and an anomaly detection task. The results underscore the efficacy of the anomaly detection approach, showcasing its ability to identify missing bolts robustly. Utilizing a dataset of 3D images acquired from a diagnostic train, treated as depth maps, the paper formulates the problem as an unsupervised learning task, training and evaluating autoencoders for anomaly detection. This research contributes to advancing quality control processes by applying deep learning in critical infrastructure monitoring.

Paper Citation

in Harvard Style

Vadakkum Vadukkal U., Cardellicchio A., Mosca N., di Summa M., Nitti M., Stella E. and Renò V. (2024). Enhancing Railway Safety: An Unsupervised Approach for Detecting Missing Bolts with Deep Learning and 3D Imaging. In Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM; ISBN 978-989-758-684-2, SciTePress, pages 924-929. DOI: 10.5220/0012570300003654

in Bibtex Style

@conference{icpram24,
author={Udith Krishnan Vadakkum Vadukkal and Angelo Cardellicchio and Nicola Mosca and Maria di Summa and Massimiliano Nitti and Ettore Stella and Vito Renò},
title={Enhancing Railway Safety: An Unsupervised Approach for Detecting Missing Bolts with Deep Learning and 3D Imaging},
booktitle={Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM},
year={2024},
pages={924-929},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012570300003654},
isbn={978-989-758-684-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM
TI - Enhancing Railway Safety: An Unsupervised Approach for Detecting Missing Bolts with Deep Learning and 3D Imaging
SN - 978-989-758-684-2
AU - Vadakkum Vadukkal U.
AU - Cardellicchio A.
AU - Mosca N.
AU - di Summa M.
AU - Nitti M.
AU - Stella E.
AU - Renò V.
PY - 2024
SP - 924
EP - 929
DO - 10.5220/0012570300003654
PB - SciTePress