A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Improving Crack Detection on Concrete Structures Using Real-World Data Augmentation for Deep Learning Convolutional Neural Networks
https://orcid.org/http://orcid.org/0009-0003-1573-6387
https://orcid.org/http://orcid.org/0000-0002-8633-3847
https://orcid.org/http://orcid.org/0009-0000-5054-8144
https://orcid.org/http://orcid.org/0009-0008-9169-2642
Civil infrastructure materials deteriorate over time due to various physical and chemical processes, such as corrosion and thermal cycles. Surface cracks on concrete structures are often the initial indicator of degradation, making it essential to assess their nature, extent, and dimensions to determine the current state of the structure and take preventive measures to avoid future damage. However, traditional manual and visual inspection methods can be labor-intensive, hazardous, and subject to subjectivity and error, making it challenging to track the evolution of defects between inspections. Deep learning convolutional neural network (CNN) algorithms, such as Mask R-CNN, provide a high level of abstraction and generalization that is achieved through training on extensively annotated datasets. These algorithms have the potential to accurately segment cracks in images, thus providing a reliable and efficient means of assessing the state of concrete structures. However, publicly available crack datasets used for training the network often contain idealized crack images without real-world noise, such as dirt, leakages, or graffiti. Our study demonstrates that adding real-world features to a dataset and augmenting the amount of data samples can improve the accuracy of the network. We utilize the publicly available CRACK500 dataset and modify it by eliminating low-quality samples and adding real graffiti patterns. By doing this, the network was able to differentiate between cracks from graffiti and wet concrete marks on real-world images, achieving a precision of 97.8% and a recall of 53.1%.
Improving Crack Detection on Concrete Structures Using Real-World Data Augmentation for Deep Learning Convolutional Neural Networks
https://orcid.org/http://orcid.org/0009-0003-1573-6387
https://orcid.org/http://orcid.org/0000-0002-8633-3847
https://orcid.org/http://orcid.org/0009-0000-5054-8144
https://orcid.org/http://orcid.org/0009-0008-9169-2642
Civil infrastructure materials deteriorate over time due to various physical and chemical processes, such as corrosion and thermal cycles. Surface cracks on concrete structures are often the initial indicator of degradation, making it essential to assess their nature, extent, and dimensions to determine the current state of the structure and take preventive measures to avoid future damage. However, traditional manual and visual inspection methods can be labor-intensive, hazardous, and subject to subjectivity and error, making it challenging to track the evolution of defects between inspections. Deep learning convolutional neural network (CNN) algorithms, such as Mask R-CNN, provide a high level of abstraction and generalization that is achieved through training on extensively annotated datasets. These algorithms have the potential to accurately segment cracks in images, thus providing a reliable and efficient means of assessing the state of concrete structures. However, publicly available crack datasets used for training the network often contain idealized crack images without real-world noise, such as dirt, leakages, or graffiti. Our study demonstrates that adding real-world features to a dataset and augmenting the amount of data samples can improve the accuracy of the network. We utilize the publicly available CRACK500 dataset and modify it by eliminating low-quality samples and adding real graffiti patterns. By doing this, the network was able to differentiate between cracks from graffiti and wet concrete marks on real-world images, achieving a precision of 97.8% and a recall of 53.1%.
Improving Crack Detection on Concrete Structures Using Real-World Data Augmentation for Deep Learning Convolutional Neural Networks
https://orcid.org/http://orcid.org/0009-0003-1573-6387
https://orcid.org/http://orcid.org/0000-0002-8633-3847
https://orcid.org/http://orcid.org/0009-0000-5054-8144
https://orcid.org/http://orcid.org/0009-0008-9169-2642
Civil infrastructure materials deteriorate over time due to various physical and chemical processes, such as corrosion and thermal cycles. Surface cracks on concrete structures are often the initial indicator of degradation, making it essential to assess their nature, extent, and dimensions to determine the current state of the structure and take preventive measures to avoid future damage. However, traditional manual and visual inspection methods can be labor-intensive, hazardous, and subject to subjectivity and error, making it challenging to track the evolution of defects between inspections. Deep learning convolutional neural network (CNN) algorithms, such as Mask R-CNN, provide a high level of abstraction and generalization that is achieved through training on extensively annotated datasets. These algorithms have the potential to accurately segment cracks in images, thus providing a reliable and efficient means of assessing the state of concrete structures. However, publicly available crack datasets used for training the network often contain idealized crack images without real-world noise, such as dirt, leakages, or graffiti. Our study demonstrates that adding real-world features to a dataset and augmenting the amount of data samples can improve the accuracy of the network. We utilize the publicly available CRACK500 dataset and modify it by eliminating low-quality samples and adding real graffiti patterns. By doing this, the network was able to differentiate between cracks from graffiti and wet concrete marks on real-world images, achieving a precision of 97.8% and a recall of 53.1%.
Improving Crack Detection on Concrete Structures Using Real-World Data Augmentation for Deep Learning Convolutional Neural Networks
Lecture Notes in Civil Engineering
Desjardins, Serge (editor) / Poitras, Gérard J. (editor) / Nik-Bakht, Mazdak (editor) / Tello-Gil, Carlos (author) / Jabari, Shabnam (author) / Waugh, Lloyd (author) / Masry, Mark (author) / McGinn, Jared (author)
Canadian Society of Civil Engineering Annual Conference ; 2023 ; Moncton, NB, Canada
Proceedings of the Canadian Society for Civil Engineering Annual Conference 2023, Volume 4 ; Chapter: 18 ; 237-249
2024-09-18
13 pages
Article/Chapter (Book)
Electronic Resource
English
Deep Learning‐Based Crack Damage Detection Using Convolutional Neural Networks
| Online Contents | 2017
Structural crack detection using deep convolutional neural networks
| Elsevier | 2021
Autonomous concrete crack detection using deep fully convolutional neural network
| British Library Online Contents | 2019