Crack recognition automation in concrete bridges using Deep Convolutional Neural Networks

Using Unmanned Aerial Systems (UASs) for bridge visual inspection automation necessitates the implementation of Deep Convolutional Neural Networks (DCNNs) to process efficiently the large amount of data collected by the UASs sensors. However, these networks require massive training datasets for the...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Zoubir Hajar, Rguig Mustapha, Elaroussi Mohammed
Formato:	article
Lenguaje:	EN FR
Publicado:	EDP Sciences 2021
Materias:	visual inspection bridge concrete crack recognition dataset deep convolutional neural network Engineering (General). Civil engineering (General) TA1-2040
Acceso en línea:	https://doaj.org/article/b3f39a0efa384d68b2a628e82011f632
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:b3f39a0efa384d68b2a628e82011f632
record_format	dspace
spelling	oai:doaj.org-article:b3f39a0efa384d68b2a628e82011f6322021-12-02T17:13:46ZCrack recognition automation in concrete bridges using Deep Convolutional Neural Networks2261-236X10.1051/matecconf/202134903014https://doaj.org/article/b3f39a0efa384d68b2a628e82011f6322021-01-01T00:00:00Zhttps://www.matec-conferences.org/articles/matecconf/pdf/2021/18/matecconf_iceaf2021_03014.pdfhttps://doaj.org/toc/2261-236XUsing Unmanned Aerial Systems (UASs) for bridge visual inspection automation necessitates the implementation of Deep Convolutional Neural Networks (DCNNs) to process efficiently the large amount of data collected by the UASs sensors. However, these networks require massive training datasets for the defects recognition and detection tasks. In an effort to expand existing concrete defects datasets, particularly concrete cracks in bridges, this paper proposes a public benchmark annotated image dataset containing over 6900 images of cracked and non cracked concrete bridges and culverts. The presented dataset includes some challenging surface conditions and covers concrete cracks with different sizes and patterns. The authors analyzed the proposed dataset using three state of the art DCNNs in Transfer Learning mode. The three models were used to classify the cracked and non cracked images and the best testing accuracy obtained reached 95.89%. The experimental results showcase the potential use of this dataset to train deep networks for concrete crack recognition in bridges. The dataset is publicly available at https://github.com/MCBDD-ZRE/Concrete-Bridge-Crack-Dataset- for academic purposes.Zoubir HajarRguig MustaphaElaroussi MohammedEDP Sciencesarticlevisual inspectionbridge concrete crack recognitiondatasetdeep convolutional neural networkEngineering (General). Civil engineering (General)TA1-2040ENFRMATEC Web of Conferences, Vol 349, p 03014 (2021)
institution	DOAJ
collection	DOAJ
language	EN FR
topic	visual inspection bridge concrete crack recognition dataset deep convolutional neural network Engineering (General). Civil engineering (General) TA1-2040
spellingShingle	visual inspection bridge concrete crack recognition dataset deep convolutional neural network Engineering (General). Civil engineering (General) TA1-2040 Zoubir Hajar Rguig Mustapha Elaroussi Mohammed Crack recognition automation in concrete bridges using Deep Convolutional Neural Networks
description	Using Unmanned Aerial Systems (UASs) for bridge visual inspection automation necessitates the implementation of Deep Convolutional Neural Networks (DCNNs) to process efficiently the large amount of data collected by the UASs sensors. However, these networks require massive training datasets for the defects recognition and detection tasks. In an effort to expand existing concrete defects datasets, particularly concrete cracks in bridges, this paper proposes a public benchmark annotated image dataset containing over 6900 images of cracked and non cracked concrete bridges and culverts. The presented dataset includes some challenging surface conditions and covers concrete cracks with different sizes and patterns. The authors analyzed the proposed dataset using three state of the art DCNNs in Transfer Learning mode. The three models were used to classify the cracked and non cracked images and the best testing accuracy obtained reached 95.89%. The experimental results showcase the potential use of this dataset to train deep networks for concrete crack recognition in bridges. The dataset is publicly available at https://github.com/MCBDD-ZRE/Concrete-Bridge-Crack-Dataset- for academic purposes.
format	article
author	Zoubir Hajar Rguig Mustapha Elaroussi Mohammed
author_facet	Zoubir Hajar Rguig Mustapha Elaroussi Mohammed
author_sort	Zoubir Hajar
title	Crack recognition automation in concrete bridges using Deep Convolutional Neural Networks
title_short	Crack recognition automation in concrete bridges using Deep Convolutional Neural Networks
title_full	Crack recognition automation in concrete bridges using Deep Convolutional Neural Networks
title_fullStr	Crack recognition automation in concrete bridges using Deep Convolutional Neural Networks
title_full_unstemmed	Crack recognition automation in concrete bridges using Deep Convolutional Neural Networks
title_sort	crack recognition automation in concrete bridges using deep convolutional neural networks
publisher	EDP Sciences
publishDate	2021
url	https://doaj.org/article/b3f39a0efa384d68b2a628e82011f632
work_keys_str_mv	AT zoubirhajar crackrecognitionautomationinconcretebridgesusingdeepconvolutionalneuralnetworks AT rguigmustapha crackrecognitionautomationinconcretebridgesusingdeepconvolutionalneuralnetworks AT elaroussimohammed crackrecognitionautomationinconcretebridgesusingdeepconvolutionalneuralnetworks
_version_	1718381339782152192

Crack recognition automation in concrete bridges using Deep Convolutional Neural Networks

Ejemplares similares