UAVs in rail damage image diagnostics supported by deep-learning networks

The article uses images from Unmanned Aerial Vehicles (UAVs) for rail diagnostics. The main advantage of such a solution compared to traditional surveys performed with measuring vehicles is the elimination of decreased train traffic. The authors, in the study, limited themselves to the diagnosis of...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Bojarczak Piotr, Lesiak Piotr
Formato:	article
Lenguaje:	EN
Publicado:	De Gruyter 2021
Materias:	unmanned aerial vehicles split defect in rail deep-learning networks Engineering (General). Civil engineering (General) TA1-2040
Acceso en línea:	https://doaj.org/article/2a33549a014840ab92eb6c05f2fd0437
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:2a33549a014840ab92eb6c05f2fd0437
record_format	dspace
spelling	oai:doaj.org-article:2a33549a014840ab92eb6c05f2fd04372021-12-05T14:10:46ZUAVs in rail damage image diagnostics supported by deep-learning networks2391-543910.1515/eng-2021-0033https://doaj.org/article/2a33549a014840ab92eb6c05f2fd04372021-01-01T00:00:00Zhttps://doi.org/10.1515/eng-2021-0033https://doaj.org/toc/2391-5439The article uses images from Unmanned Aerial Vehicles (UAVs) for rail diagnostics. The main advantage of such a solution compared to traditional surveys performed with measuring vehicles is the elimination of decreased train traffic. The authors, in the study, limited themselves to the diagnosis of hazardous split defects in rails. An algorithm has been proposed to detect them with an efficiency rate of about 81% for defects not less than 6.9% of the rail head width. It uses the FCN-8 deep-learning network, implemented in the Tensorflow environment, to extract the rail head by image segmentation. Using this type of network for segmentation increases the resistance of the algorithm to changes in the recorded rail image brightness. This is of fundamental importance in the case of variable conditions for image recording by UAVs. The detection of these defects in the rail head is performed using an algorithm in the Python language and the OpenCV library. To locate the defect, it uses the contour of a separate rail head together with a rectangle circumscribed around it. The use of UAVs together with artificial intelligence to detect split defects is an important element of novelty presented in this work.Bojarczak PiotrLesiak PiotrDe Gruyterarticleunmanned aerial vehiclessplit defect in raildeep-learning networksEngineering (General). Civil engineering (General)TA1-2040ENOpen Engineering, Vol 11, Iss 1, Pp 339-348 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	unmanned aerial vehicles split defect in rail deep-learning networks Engineering (General). Civil engineering (General) TA1-2040
spellingShingle	unmanned aerial vehicles split defect in rail deep-learning networks Engineering (General). Civil engineering (General) TA1-2040 Bojarczak Piotr Lesiak Piotr UAVs in rail damage image diagnostics supported by deep-learning networks
description	The article uses images from Unmanned Aerial Vehicles (UAVs) for rail diagnostics. The main advantage of such a solution compared to traditional surveys performed with measuring vehicles is the elimination of decreased train traffic. The authors, in the study, limited themselves to the diagnosis of hazardous split defects in rails. An algorithm has been proposed to detect them with an efficiency rate of about 81% for defects not less than 6.9% of the rail head width. It uses the FCN-8 deep-learning network, implemented in the Tensorflow environment, to extract the rail head by image segmentation. Using this type of network for segmentation increases the resistance of the algorithm to changes in the recorded rail image brightness. This is of fundamental importance in the case of variable conditions for image recording by UAVs. The detection of these defects in the rail head is performed using an algorithm in the Python language and the OpenCV library. To locate the defect, it uses the contour of a separate rail head together with a rectangle circumscribed around it. The use of UAVs together with artificial intelligence to detect split defects is an important element of novelty presented in this work.
format	article
author	Bojarczak Piotr Lesiak Piotr
author_facet	Bojarczak Piotr Lesiak Piotr
author_sort	Bojarczak Piotr
title	UAVs in rail damage image diagnostics supported by deep-learning networks
title_short	UAVs in rail damage image diagnostics supported by deep-learning networks
title_full	UAVs in rail damage image diagnostics supported by deep-learning networks
title_fullStr	UAVs in rail damage image diagnostics supported by deep-learning networks
title_full_unstemmed	UAVs in rail damage image diagnostics supported by deep-learning networks
title_sort	uavs in rail damage image diagnostics supported by deep-learning networks
publisher	De Gruyter
publishDate	2021
url	https://doaj.org/article/2a33549a014840ab92eb6c05f2fd0437
work_keys_str_mv	AT bojarczakpiotr uavsinraildamageimagediagnosticssupportedbydeeplearningnetworks AT lesiakpiotr uavsinraildamageimagediagnosticssupportedbydeeplearningnetworks
_version_	1718371710503223296

UAVs in rail damage image diagnostics supported by deep-learning networks

Ejemplares similares