An Investigation of Railway Fastener Detection Using Image Processing and Augmented Deep Learning

The rail fastening system forms an indispensable part of the rail tracks and needs to be periodically inspected to ensure safe, reliable and sustainable rail operations. Automated visual inspection has gained significant importance for fastener inspection in recent years. Position accuracy, robustne...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Praneeth Chandran, Johnny Asber, Florian Thiery, Johan Odelius, Matti Rantatalo
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	rail fastening system clamps image processing deep learning Environmental effects of industries and plants TD194-195 Renewable energy sources TJ807-830 Environmental sciences GE1-350
Acceso en línea:	https://doaj.org/article/ee7a14531d014f3995e8c856b3065575
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:ee7a14531d014f3995e8c856b3065575
record_format	dspace
spelling	oai:doaj.org-article:ee7a14531d014f3995e8c856b30655752021-11-11T19:42:21ZAn Investigation of Railway Fastener Detection Using Image Processing and Augmented Deep Learning10.3390/su1321120512071-1050https://doaj.org/article/ee7a14531d014f3995e8c856b30655752021-10-01T00:00:00Zhttps://www.mdpi.com/2071-1050/13/21/12051https://doaj.org/toc/2071-1050The rail fastening system forms an indispensable part of the rail tracks and needs to be periodically inspected to ensure safe, reliable and sustainable rail operations. Automated visual inspection has gained significant importance for fastener inspection in recent years. Position accuracy, robustness, and practical limitations due to the complex environment are some of the major concerns associated with this method. This study investigates the combined use of image processing and deep learning algorithms for detecting missing clamps within a rail fastening system. The images used for this study was acquired during field inspections carried out along the Borlänge-Avesta line in Sweden. The image processing techniques proposed in this study enabled the improvement of the fastener position and removal of redundant information from the fastener images. In addition, image augmentation was carried out to enhance the data set, ensure experimental reliability and replicate practical challenges associated with such visual inspection. Convolutional neural network and ResNet-50 algorithms are used for classification purposes, and both the algorithms achieved over 98% accuracy during training and validation and over 94% accuracy during the test stage. Both the algorithms also maintained a good balance between the precision and recall scores during the test stage. CNN and ResNet-50 algorithms were also tested to analyse their performances when the clamp areas were covered. CNN was able to accurately predict the fastener state up to 70% of clamp area occlusion, and ResNet-50 was able to achieve accurate predictions up to 75% of clamp area occlusion.Praneeth ChandranJohnny AsberFlorian ThieryJohan OdeliusMatti RantataloMDPI AGarticlerail fastening systemclampsimage processingdeep learningEnvironmental effects of industries and plantsTD194-195Renewable energy sourcesTJ807-830Environmental sciencesGE1-350ENSustainability, Vol 13, Iss 12051, p 12051 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	rail fastening system clamps image processing deep learning Environmental effects of industries and plants TD194-195 Renewable energy sources TJ807-830 Environmental sciences GE1-350
spellingShingle	rail fastening system clamps image processing deep learning Environmental effects of industries and plants TD194-195 Renewable energy sources TJ807-830 Environmental sciences GE1-350 Praneeth Chandran Johnny Asber Florian Thiery Johan Odelius Matti Rantatalo An Investigation of Railway Fastener Detection Using Image Processing and Augmented Deep Learning
description	The rail fastening system forms an indispensable part of the rail tracks and needs to be periodically inspected to ensure safe, reliable and sustainable rail operations. Automated visual inspection has gained significant importance for fastener inspection in recent years. Position accuracy, robustness, and practical limitations due to the complex environment are some of the major concerns associated with this method. This study investigates the combined use of image processing and deep learning algorithms for detecting missing clamps within a rail fastening system. The images used for this study was acquired during field inspections carried out along the Borlänge-Avesta line in Sweden. The image processing techniques proposed in this study enabled the improvement of the fastener position and removal of redundant information from the fastener images. In addition, image augmentation was carried out to enhance the data set, ensure experimental reliability and replicate practical challenges associated with such visual inspection. Convolutional neural network and ResNet-50 algorithms are used for classification purposes, and both the algorithms achieved over 98% accuracy during training and validation and over 94% accuracy during the test stage. Both the algorithms also maintained a good balance between the precision and recall scores during the test stage. CNN and ResNet-50 algorithms were also tested to analyse their performances when the clamp areas were covered. CNN was able to accurately predict the fastener state up to 70% of clamp area occlusion, and ResNet-50 was able to achieve accurate predictions up to 75% of clamp area occlusion.
format	article
author	Praneeth Chandran Johnny Asber Florian Thiery Johan Odelius Matti Rantatalo
author_facet	Praneeth Chandran Johnny Asber Florian Thiery Johan Odelius Matti Rantatalo
author_sort	Praneeth Chandran
title	An Investigation of Railway Fastener Detection Using Image Processing and Augmented Deep Learning
title_short	An Investigation of Railway Fastener Detection Using Image Processing and Augmented Deep Learning
title_full	An Investigation of Railway Fastener Detection Using Image Processing and Augmented Deep Learning
title_fullStr	An Investigation of Railway Fastener Detection Using Image Processing and Augmented Deep Learning
title_full_unstemmed	An Investigation of Railway Fastener Detection Using Image Processing and Augmented Deep Learning
title_sort	investigation of railway fastener detection using image processing and augmented deep learning
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/ee7a14531d014f3995e8c856b3065575
work_keys_str_mv	AT praneethchandran aninvestigationofrailwayfastenerdetectionusingimageprocessingandaugmenteddeeplearning AT johnnyasber aninvestigationofrailwayfastenerdetectionusingimageprocessingandaugmenteddeeplearning AT florianthiery aninvestigationofrailwayfastenerdetectionusingimageprocessingandaugmenteddeeplearning AT johanodelius aninvestigationofrailwayfastenerdetectionusingimageprocessingandaugmenteddeeplearning AT mattirantatalo aninvestigationofrailwayfastenerdetectionusingimageprocessingandaugmenteddeeplearning AT praneethchandran investigationofrailwayfastenerdetectionusingimageprocessingandaugmenteddeeplearning AT johnnyasber investigationofrailwayfastenerdetectionusingimageprocessingandaugmenteddeeplearning AT florianthiery investigationofrailwayfastenerdetectionusingimageprocessingandaugmenteddeeplearning AT johanodelius investigationofrailwayfastenerdetectionusingimageprocessingandaugmenteddeeplearning AT mattirantatalo investigationofrailwayfastenerdetectionusingimageprocessingandaugmenteddeeplearning
_version_	1718431501589151744

An Investigation of Railway Fastener Detection Using Image Processing and Augmented Deep Learning

Ejemplares similares