Cargando…
Road Surface Crack Detection Method Based on Conditional Generative Adversarial Networks
Constant monitoring of road surfaces helps to show the urgency of deterioration or problems in the road construction and to improve the safety level of the road surface. Conditional generative adversarial networks (cGAN) are a powerful tool to generate or transform the images used for crack detectio...
Autores principales: | , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8587934/ https://www.ncbi.nlm.nih.gov/pubmed/34770711 http://dx.doi.org/10.3390/s21217405 |
_version_ | 1784598302609637376 |
---|---|
author | Kyslytsyna, Anastasiia Xia, Kewen Kislitsyn, Artem Abd El Kader, Isselmou Wu, Youxi |
author_facet | Kyslytsyna, Anastasiia Xia, Kewen Kislitsyn, Artem Abd El Kader, Isselmou Wu, Youxi |
author_sort | Kyslytsyna, Anastasiia |
collection | PubMed |
description | Constant monitoring of road surfaces helps to show the urgency of deterioration or problems in the road construction and to improve the safety level of the road surface. Conditional generative adversarial networks (cGAN) are a powerful tool to generate or transform the images used for crack detection. The advantage of this method is the highly accurate results in vector-based images, which are convenient for mathematical analysis of the detected cracks at a later time. However, images taken under established parameters are different from images in real-world contexts. Another potential problem of cGAN is that it is difficult to detect the shape of an object when the resulting accuracy is low, which can seriously affect any further mathematical analysis of the detected crack. To tackle this issue, this paper proposes a method called improved cGAN with attention gate (ICGA) for roadway surface crack detection. To obtain a more accurate shape of the detected target object, ICGA establishes a multi-level model with independent stages. In the first stage, everything except the road is treated as noise and removed from the image. These images are stored in a new dataset. In the second stage, ICGA determines the cracks. Therefore, ICGA focuses on the redistribution of cracks, not the auxiliary elements in the image. ICGA adds two attention gates to a U-net architecture and improves the segmentation capacities of the generator in pix2pix. Extensive experimental results on dashboard camera images of the Unsupervised Llamas dataset show that our method has better performance than other state-of-the-art methods. |
format | Online Article Text |
id | pubmed-8587934 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-85879342021-11-13 Road Surface Crack Detection Method Based on Conditional Generative Adversarial Networks Kyslytsyna, Anastasiia Xia, Kewen Kislitsyn, Artem Abd El Kader, Isselmou Wu, Youxi Sensors (Basel) Article Constant monitoring of road surfaces helps to show the urgency of deterioration or problems in the road construction and to improve the safety level of the road surface. Conditional generative adversarial networks (cGAN) are a powerful tool to generate or transform the images used for crack detection. The advantage of this method is the highly accurate results in vector-based images, which are convenient for mathematical analysis of the detected cracks at a later time. However, images taken under established parameters are different from images in real-world contexts. Another potential problem of cGAN is that it is difficult to detect the shape of an object when the resulting accuracy is low, which can seriously affect any further mathematical analysis of the detected crack. To tackle this issue, this paper proposes a method called improved cGAN with attention gate (ICGA) for roadway surface crack detection. To obtain a more accurate shape of the detected target object, ICGA establishes a multi-level model with independent stages. In the first stage, everything except the road is treated as noise and removed from the image. These images are stored in a new dataset. In the second stage, ICGA determines the cracks. Therefore, ICGA focuses on the redistribution of cracks, not the auxiliary elements in the image. ICGA adds two attention gates to a U-net architecture and improves the segmentation capacities of the generator in pix2pix. Extensive experimental results on dashboard camera images of the Unsupervised Llamas dataset show that our method has better performance than other state-of-the-art methods. MDPI 2021-11-08 /pmc/articles/PMC8587934/ /pubmed/34770711 http://dx.doi.org/10.3390/s21217405 Text en © 2021 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 Kyslytsyna, Anastasiia Xia, Kewen Kislitsyn, Artem Abd El Kader, Isselmou Wu, Youxi Road Surface Crack Detection Method Based on Conditional Generative Adversarial Networks |
title | Road Surface Crack Detection Method Based on Conditional Generative Adversarial Networks |
title_full | Road Surface Crack Detection Method Based on Conditional Generative Adversarial Networks |
title_fullStr | Road Surface Crack Detection Method Based on Conditional Generative Adversarial Networks |
title_full_unstemmed | Road Surface Crack Detection Method Based on Conditional Generative Adversarial Networks |
title_short | Road Surface Crack Detection Method Based on Conditional Generative Adversarial Networks |
title_sort | road surface crack detection method based on conditional generative adversarial networks |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8587934/ https://www.ncbi.nlm.nih.gov/pubmed/34770711 http://dx.doi.org/10.3390/s21217405 |
work_keys_str_mv | AT kyslytsynaanastasiia roadsurfacecrackdetectionmethodbasedonconditionalgenerativeadversarialnetworks AT xiakewen roadsurfacecrackdetectionmethodbasedonconditionalgenerativeadversarialnetworks AT kislitsynartem roadsurfacecrackdetectionmethodbasedonconditionalgenerativeadversarialnetworks AT abdelkaderisselmou roadsurfacecrackdetectionmethodbasedonconditionalgenerativeadversarialnetworks AT wuyouxi roadsurfacecrackdetectionmethodbasedonconditionalgenerativeadversarialnetworks |