Cargando…

Combining the YOLOv4 Deep Learning Model with UAV Imagery Processing Technology in the Extraction and Quantization of Cracks in Bridges

Bridges are often at risk due to the effects of natural disasters, such as earthquakes and typhoons. Bridge inspection assessments normally focus on cracks. However, numerous concrete structures with cracked surfaces are highly elevated or over water, and is not easily accessible to a bridge inspect...

Descripción completa

Detalles Bibliográficos
Autores principales: Kao, Szu-Pyng, Chang, Yung-Chen, Wang, Feng-Liang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10007411/
https://www.ncbi.nlm.nih.gov/pubmed/36904775
http://dx.doi.org/10.3390/s23052572
_version_ 1784905514615832576
author Kao, Szu-Pyng
Chang, Yung-Chen
Wang, Feng-Liang
author_facet Kao, Szu-Pyng
Chang, Yung-Chen
Wang, Feng-Liang
author_sort Kao, Szu-Pyng
collection PubMed
description Bridges are often at risk due to the effects of natural disasters, such as earthquakes and typhoons. Bridge inspection assessments normally focus on cracks. However, numerous concrete structures with cracked surfaces are highly elevated or over water, and is not easily accessible to a bridge inspector. Furthermore, poor lighting under bridges and a complex visual background can hinder inspectors in their identification and measurement of cracks. In this study, cracks on bridge surfaces were photographed using a UAV-mounted camera. A YOLOv4 deep learning model was used to train a model for identifying cracks; the model was then employed in object detection. To perform the quantitative crack test, the images with identified cracks were first converted to grayscale images and then to binary images the using local thresholding method. Next, the two edge detection methods, Canny and morphological edge detectors were applied to the binary images to extract the edges of the cracks and obtain two types of crack edge images. Then, two scale methods, the planar marker method, and the total station measurement method, were used to calculate the actual size of the crack edge image. The results indicated that the model had an accuracy of 92%, with width measurements as precise as 0.22 mm. The proposed approach can thus enable bridge inspections and obtain objective and quantitative data.
format Online
Article
Text
id pubmed-10007411
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-100074112023-03-12 Combining the YOLOv4 Deep Learning Model with UAV Imagery Processing Technology in the Extraction and Quantization of Cracks in Bridges Kao, Szu-Pyng Chang, Yung-Chen Wang, Feng-Liang Sensors (Basel) Article Bridges are often at risk due to the effects of natural disasters, such as earthquakes and typhoons. Bridge inspection assessments normally focus on cracks. However, numerous concrete structures with cracked surfaces are highly elevated or over water, and is not easily accessible to a bridge inspector. Furthermore, poor lighting under bridges and a complex visual background can hinder inspectors in their identification and measurement of cracks. In this study, cracks on bridge surfaces were photographed using a UAV-mounted camera. A YOLOv4 deep learning model was used to train a model for identifying cracks; the model was then employed in object detection. To perform the quantitative crack test, the images with identified cracks were first converted to grayscale images and then to binary images the using local thresholding method. Next, the two edge detection methods, Canny and morphological edge detectors were applied to the binary images to extract the edges of the cracks and obtain two types of crack edge images. Then, two scale methods, the planar marker method, and the total station measurement method, were used to calculate the actual size of the crack edge image. The results indicated that the model had an accuracy of 92%, with width measurements as precise as 0.22 mm. The proposed approach can thus enable bridge inspections and obtain objective and quantitative data. MDPI 2023-02-25 /pmc/articles/PMC10007411/ /pubmed/36904775 http://dx.doi.org/10.3390/s23052572 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Kao, Szu-Pyng
Chang, Yung-Chen
Wang, Feng-Liang
Combining the YOLOv4 Deep Learning Model with UAV Imagery Processing Technology in the Extraction and Quantization of Cracks in Bridges
title Combining the YOLOv4 Deep Learning Model with UAV Imagery Processing Technology in the Extraction and Quantization of Cracks in Bridges
title_full Combining the YOLOv4 Deep Learning Model with UAV Imagery Processing Technology in the Extraction and Quantization of Cracks in Bridges
title_fullStr Combining the YOLOv4 Deep Learning Model with UAV Imagery Processing Technology in the Extraction and Quantization of Cracks in Bridges
title_full_unstemmed Combining the YOLOv4 Deep Learning Model with UAV Imagery Processing Technology in the Extraction and Quantization of Cracks in Bridges
title_short Combining the YOLOv4 Deep Learning Model with UAV Imagery Processing Technology in the Extraction and Quantization of Cracks in Bridges
title_sort combining the yolov4 deep learning model with uav imagery processing technology in the extraction and quantization of cracks in bridges
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10007411/
https://www.ncbi.nlm.nih.gov/pubmed/36904775
http://dx.doi.org/10.3390/s23052572
work_keys_str_mv AT kaoszupyng combiningtheyolov4deeplearningmodelwithuavimageryprocessingtechnologyintheextractionandquantizationofcracksinbridges
AT changyungchen combiningtheyolov4deeplearningmodelwithuavimageryprocessingtechnologyintheextractionandquantizationofcracksinbridges
AT wangfengliang combiningtheyolov4deeplearningmodelwithuavimageryprocessingtechnologyintheextractionandquantizationofcracksinbridges