Image-Based Concrete Crack Detection Using Convolutional Neural Network and Exhaustive Search Technique
Crack detection is important for the inspection and evaluation during the maintenance of concrete structures. However, conventional image-based methods need extract crack features using complex image preprocessing techniques, so it can lead to challenges when concrete surface contains various types...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2019-01-01
|
| Series: | Advances in Civil Engineering |
| Online Access: | http://dx.doi.org/10.1155/2019/6520620 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841524402561220608 |
|---|---|
| author | Shengyuan Li Xuefeng Zhao |
| author_facet | Shengyuan Li Xuefeng Zhao |
| author_sort | Shengyuan Li |
| collection | DOAJ |
| description | Crack detection is important for the inspection and evaluation during the maintenance of concrete structures. However, conventional image-based methods need extract crack features using complex image preprocessing techniques, so it can lead to challenges when concrete surface contains various types of noise due to extensively varying real-world situations such as thin cracks, rough surface, shadows, etc. To overcome these challenges, this paper proposes an image-based crack detection method using a deep convolutional neural network (CNN). A CNN is designed through modifying AlexNet and then trained and validated using a built database with 60000 images. Through comparing validation accuracy under different base learning rates, 0.01 was chosen as the best base learning rate with the highest validation accuracy of 99.06%, and its training result is used in the following testing process. The robustness and adaptability of the trained CNN are tested on 205 images with 3120 × 4160 pixel resolutions which were not used for training and validation. The trained CNN is integrated into a smartphone application to mobile more public to detect cracks in practice. The results confirm that the proposed method can indeed detect cracks in images from real concrete surfaces. |
| format | Article |
| id | doaj-art-91023fad575445099259ce8d4234d833 |
| institution | Kabale University |
| issn | 1687-8086 1687-8094 |
| language | English |
| publishDate | 2019-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Advances in Civil Engineering |
| spelling | doaj-art-91023fad575445099259ce8d4234d8332025-02-03T05:53:14ZengWileyAdvances in Civil Engineering1687-80861687-80942019-01-01201910.1155/2019/65206206520620Image-Based Concrete Crack Detection Using Convolutional Neural Network and Exhaustive Search TechniqueShengyuan Li0Xuefeng Zhao1School of Civil Engineering, State Key Laboratory of Coastal and Offshore Engineering, Dalian University of Technology, 116023 Dalian, ChinaSchool of Civil Engineering, State Key Laboratory of Coastal and Offshore Engineering, Dalian University of Technology, 116023 Dalian, ChinaCrack detection is important for the inspection and evaluation during the maintenance of concrete structures. However, conventional image-based methods need extract crack features using complex image preprocessing techniques, so it can lead to challenges when concrete surface contains various types of noise due to extensively varying real-world situations such as thin cracks, rough surface, shadows, etc. To overcome these challenges, this paper proposes an image-based crack detection method using a deep convolutional neural network (CNN). A CNN is designed through modifying AlexNet and then trained and validated using a built database with 60000 images. Through comparing validation accuracy under different base learning rates, 0.01 was chosen as the best base learning rate with the highest validation accuracy of 99.06%, and its training result is used in the following testing process. The robustness and adaptability of the trained CNN are tested on 205 images with 3120 × 4160 pixel resolutions which were not used for training and validation. The trained CNN is integrated into a smartphone application to mobile more public to detect cracks in practice. The results confirm that the proposed method can indeed detect cracks in images from real concrete surfaces.http://dx.doi.org/10.1155/2019/6520620 |
| spellingShingle | Shengyuan Li Xuefeng Zhao Image-Based Concrete Crack Detection Using Convolutional Neural Network and Exhaustive Search Technique Advances in Civil Engineering |
| title | Image-Based Concrete Crack Detection Using Convolutional Neural Network and Exhaustive Search Technique |
| title_full | Image-Based Concrete Crack Detection Using Convolutional Neural Network and Exhaustive Search Technique |
| title_fullStr | Image-Based Concrete Crack Detection Using Convolutional Neural Network and Exhaustive Search Technique |
| title_full_unstemmed | Image-Based Concrete Crack Detection Using Convolutional Neural Network and Exhaustive Search Technique |
| title_short | Image-Based Concrete Crack Detection Using Convolutional Neural Network and Exhaustive Search Technique |
| title_sort | image based concrete crack detection using convolutional neural network and exhaustive search technique |
| url | http://dx.doi.org/10.1155/2019/6520620 |
| work_keys_str_mv | AT shengyuanli imagebasedconcretecrackdetectionusingconvolutionalneuralnetworkandexhaustivesearchtechnique AT xuefengzhao imagebasedconcretecrackdetectionusingconvolutionalneuralnetworkandexhaustivesearchtechnique |