Automatic Detection of Rail Defects from Images

Emil Hovad; Helena Hansen; André Filipe da Silva Rodrigues; Vedrana Andersen Dahl

doi:10.1007/978-3-030-62472-9_11

Automatic Detection of Rail Defects from Images

Emil Hovad^*, Helena Hansen, André Filipe da Silva Rodrigues, Vedrana Andersen Dahl

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Book chapter › Research › peer-review

Abstract

In this study, images of the rails captured by a track recording car are investigated. The images are processed in order to asses and predict the rail quality by a simple method, which gives the possibility of fast and easy implementation. The first step of the method is detecting the rails from the images with an algorithm. The second step of the method is finding visually noticeable defects on the detected rail with automatized algorithms for defect detection. One of the algorithms for defect detection shows promising results and investigating the rail images could be a promising complementary method to the already used manual ultrasound measurements.

Original language	English
Title of host publication	Intelligent Quality Assessment of Railway Switches and Crossing
Publisher	Springer
Publication date	2021
Pages	187-205
ISBN (Print)	978-3-030-62471-2
DOIs	https://doi.org/10.1007/978-3-030-62472-9_11
Publication status	Published - 2021

Series	Springer Series in Reliability Engineering
ISSN	1614-7839

Bibliographical note

Publisher Copyright:
© 2021, Springer Nature Switzerland AG.

Access to Document

10.1007/978-3-030-62472-9_11

OpenUrl availability

Full text

Cite this

@inbook{c3d6f340098646bb9486380d8168ca69,

title = "Automatic Detection of Rail Defects from Images",

abstract = "In this study, images of the rails captured by a track recording car are investigated. The images are processed in order to asses and predict the rail quality by a simple method, which gives the possibility of fast and easy implementation. The first step of the method is detecting the rails from the images with an algorithm. The second step of the method is finding visually noticeable defects on the detected rail with automatized algorithms for defect detection. One of the algorithms for defect detection shows promising results and investigating the rail images could be a promising complementary method to the already used manual ultrasound measurements.",

author = "Emil Hovad and Helena Hansen and {da Silva Rodrigues}, {Andr{\'e} Filipe} and Dahl, {Vedrana Andersen}",

note = "Publisher Copyright: {\textcopyright} 2021, Springer Nature Switzerland AG.",

year = "2021",

doi = "10.1007/978-3-030-62472-9_11",

language = "English",

isbn = "978-3-030-62471-2",

series = "Springer Series in Reliability Engineering",

publisher = "Springer",

pages = "187--205",

booktitle = "Intelligent Quality Assessment of Railway Switches and Crossing",

}

TY - CHAP

T1 - Automatic Detection of Rail Defects from Images

AU - Hovad, Emil

AU - Hansen, Helena

AU - da Silva Rodrigues, André Filipe

AU - Dahl, Vedrana Andersen

PY - 2021

Y1 - 2021

N2 - In this study, images of the rails captured by a track recording car are investigated. The images are processed in order to asses and predict the rail quality by a simple method, which gives the possibility of fast and easy implementation. The first step of the method is detecting the rails from the images with an algorithm. The second step of the method is finding visually noticeable defects on the detected rail with automatized algorithms for defect detection. One of the algorithms for defect detection shows promising results and investigating the rail images could be a promising complementary method to the already used manual ultrasound measurements.

AB - In this study, images of the rails captured by a track recording car are investigated. The images are processed in order to asses and predict the rail quality by a simple method, which gives the possibility of fast and easy implementation. The first step of the method is detecting the rails from the images with an algorithm. The second step of the method is finding visually noticeable defects on the detected rail with automatized algorithms for defect detection. One of the algorithms for defect detection shows promising results and investigating the rail images could be a promising complementary method to the already used manual ultrasound measurements.

U2 - 10.1007/978-3-030-62472-9_11

DO - 10.1007/978-3-030-62472-9_11

M3 - Book chapter

AN - SCOPUS:85102285010

SN - 978-3-030-62471-2

T3 - Springer Series in Reliability Engineering

SP - 187

EP - 205

BT - Intelligent Quality Assessment of Railway Switches and Crossing

PB - Springer