2D Digital Image Correlation and Region-Based Convolutional Neural Network in Monitoring and Evaluation of Surface Cracks in Concrete Structural Elements

2D Digital Image Correlation and Region-Based Convolutional Neural Network in Monitoring and Evaluation of Surface Cracks in Concrete Structural Elements

This paper shows how 2D digital image correlation (2D DIC) and region-based convolutional neural network (R-CNN) can be combined for image-based automated monitoring and assessment of surface crack development of concrete structural elements during laboratory quasi-static tests. In the presented app...

Full description

Bibliographic Details
Main Authors: Marek Słoński, Marcin Tekieli
Format: Article
Language:English
Published: MDPI AG 2020-08-01
Series:Materials
Subjects:
digital image correlation
region-based convolutional neural network
machine learning
crack monitoring
crack detection and localization
Online Access:https://www.mdpi.com/1996-1944/13/16/3527
id doaj-6dac817154294e9cbb5575f8396cb492
record_format Article
spelling doaj-6dac817154294e9cbb5575f8396cb4922020-11-25T02:58:23ZengMDPI AGMaterials1996-19442020-08-01133527352710.3390/ma131635272D Digital Image Correlation and Region-Based Convolutional Neural Network in Monitoring and Evaluation of Surface Cracks in Concrete Structural ElementsMarek Słoński0Marcin Tekieli1Faculty of Civil Engineering, Cracow University of Technology, ul. Warszawska 24, 31-155 Kraków, PolandFaculty of Civil Engineering, Cracow University of Technology, ul. Warszawska 24, 31-155 Kraków, PolandThis paper shows how 2D digital image correlation (2D DIC) and region-based convolutional neural network (R-CNN) can be combined for image-based automated monitoring and assessment of surface crack development of concrete structural elements during laboratory quasi-static tests. In the presented approach, the 2D DIC-based monitoring enables estimation of deformation fields on the surface of the concrete element and measurements of crack width. Moreover, the R-CNN model provides unmanned simultaneous detection and localization of multiple cracks in the images. The results show that the automatic monitoring and evaluation of crack development in concrete structural elements is possible with high accuracy and reliability.https://www.mdpi.com/1996-1944/13/16/3527digital image correlationregion-based convolutional neural networkmachine learningcrack monitoringcrack detection and localization
collection DOAJ
language English
format Article
sources DOAJ
author Marek Słoński
Marcin Tekieli
spellingShingle Marek Słoński
Marcin Tekieli
2D Digital Image Correlation and Region-Based Convolutional Neural Network in Monitoring and Evaluation of Surface Cracks in Concrete Structural Elements
Materials
digital image correlation
region-based convolutional neural network
machine learning
crack monitoring
crack detection and localization
author_facet Marek Słoński
Marcin Tekieli
author_sort Marek Słoński
title 2D Digital Image Correlation and Region-Based Convolutional Neural Network in Monitoring and Evaluation of Surface Cracks in Concrete Structural Elements
title_short 2D Digital Image Correlation and Region-Based Convolutional Neural Network in Monitoring and Evaluation of Surface Cracks in Concrete Structural Elements
title_full 2D Digital Image Correlation and Region-Based Convolutional Neural Network in Monitoring and Evaluation of Surface Cracks in Concrete Structural Elements
title_fullStr 2D Digital Image Correlation and Region-Based Convolutional Neural Network in Monitoring and Evaluation of Surface Cracks in Concrete Structural Elements
title_full_unstemmed 2D Digital Image Correlation and Region-Based Convolutional Neural Network in Monitoring and Evaluation of Surface Cracks in Concrete Structural Elements
title_sort 2d digital image correlation and region-based convolutional neural network in monitoring and evaluation of surface cracks in concrete structural elements
publisher MDPI AG
series Materials
issn 1996-1944
publishDate 2020-08-01
description This paper shows how 2D digital image correlation (2D DIC) and region-based convolutional neural network (R-CNN) can be combined for image-based automated monitoring and assessment of surface crack development of concrete structural elements during laboratory quasi-static tests. In the presented approach, the 2D DIC-based monitoring enables estimation of deformation fields on the surface of the concrete element and measurements of crack width. Moreover, the R-CNN model provides unmanned simultaneous detection and localization of multiple cracks in the images. The results show that the automatic monitoring and evaluation of crack development in concrete structural elements is possible with high accuracy and reliability.
topic digital image correlation
region-based convolutional neural network
machine learning
crack monitoring
crack detection and localization
url https://www.mdpi.com/1996-1944/13/16/3527
work_keys_str_mv AT mareksłonski 2ddigitalimagecorrelationandregionbasedconvolutionalneuralnetworkinmonitoringandevaluationofsurfacecracksinconcretestructuralelements
AT marcintekieli 2ddigitalimagecorrelationandregionbasedconvolutionalneuralnetworkinmonitoringandevaluationofsurfacecracksinconcretestructuralelements
_version_ 1724706688845479936

Similar Items