Deep Learning for Automatic Railway Maintenance

Emil Hovad*, Thomas Wix, Maxim Khomiakov, Georgios Vassos, André Filipe da Silva Rodrigues, Alejandro de Miguel Tejada, Line H. Clemmensen

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingBook chapterResearchpeer-review


We propose a computer vision system which detects defects on rails using images. Banedanmark, the Danish railway manager, conducts regular inspections of their railway infrastructure to assess the safety and efficiency of operations. Indications of defects on rails are detected by a recording car which has a system based on an eddy current system for investigating the top part of the rail and an ultra-sound system for the lower part. The proposed computer vision system is a complementary and convenient method to identify and monitor defects on rails. The computer vision system is based on the deep learning framework called YOLO v3. The detected defects are represented by bounding boxes. The system can automatically detect surface defects as well as problematic isolation joints from images of the railway track, including complex geometric sections in turnouts. On an independent test set, it is shown that the computer vision system finds defects, with classification rates of 84% for surface defects, 71% for problematic isolation joints and 74% for non-problematic isolation joints, corresponding to a macro F1-score of 81.5%. This could potentially reduce maintenance cost through automatized fault detection from the developed computer vision system.

Original languageEnglish
Title of host publicationIntelligent Quality Assessment of Railway Switches and Crossings
Publication date2021
ISBN (Print)978-3-030-62471-2
Publication statusPublished - 2021
SeriesSpringer Series in Reliability Engineering

Bibliographical note

Funding Information:
Financial support for this study was provided by funding from “Innovation Fund Denmark” under grant number: 4109-0003B-INTELLISWITCH.

Publisher Copyright:
© 2021, Springer Nature Switzerland AG.


Dive into the research topics of 'Deep Learning for Automatic Railway Maintenance'. Together they form a unique fingerprint.

Cite this