Browse > Article
http://dx.doi.org/10.9708/jksci.2020.25.10.035

A method for concrete crack detection using U-Net based image inpainting technique  

Kim, Su-Min (Epozen's research institute)
Sohn, Jung-Mo (Epozen's research institute)
Kim, Do-Soo (Epozen's research institute)
Abstract
In this study, we propose a crack detection method using limited data with a U-Net based image inpainting technique that is a modified unsupervised anomaly detection method. Concrete cracking occurs due to a variety of causes and is a factor that can cause serious damage to the structure in the long term. In general, crack investigation uses an inspector's visual inspection on the concrete surfaces, which is less objective in judgment and has a high possibility of human error. Therefore, a method with objective and accurate image analysis processing is required. In recent years, the methods using deep learning have been studied to detect cracks quickly and accurately. However, when the amount of crack data on the building or infrastructure to be inspected is small, existing crack detection models using it often show a limited performance. Therefore, in this study, an unsupervised anomaly detection method was used to augment the data on the object to be inspected, and as a result of learning using the data, we confirmed the performance of 98.78% of accuracy and 82.67% of harmonic average (F1_Score).
Keywords
Deep Learning; Concrete Crack; Crack Detection; Anomaly Detection; U-Net; Unsupervised Learning;
Citations & Related Records
Times Cited By KSCI : 2  (Citation Analysis)
연도 인용수 순위
1 Seo, Wonju, UNET, https://wewinserv.tistory.com/30
2 Ministry of Land, Infrastructure and Transport, Detailed instructions for the safety and maintenance of facilities, 2019
3 Kim, Ah-Ram, Kim, Donghyeon, Byun, Yo-Seph, Lee, Seong-Won, Crack Detection of Concrete Structure Using Deep Learning and Image Processing Method in Geotechnical Engineering. Journal of the Korean Geotechnical Society, 34(12), 145 -154., 2018, DOI:10.7843/kgs.2018.34.12.145   DOI
4 Jung, Seo-Young, Yu, Jung-Ho. A Proposal of Automatic Condition Evaluation Process based on Unsupervised Learning. Proceedings of KICEM Annual Conference, pp.79-80, 2019.
5 Lee Hoseong, Anomaly Detection Overview , https://hoya012.github.io/blog/anomaly-detection-overview-1/
6 Oh Miae, Study on anomaly detection based on Machine Learning (Report No.2018-16), Korea Institute for Health and Social Affairs, 2018
7 D. Carrera, G. Boracchi, A. Foi and B. Wohlberg, "Detecting anomalous structures by convolutional sparse models," 2015 International Joint Conference on Neural Networks (IJCNN), Killarney, 2015, pp. 1-8, doi: 10.1109/IJCNN.2015.7280790.
8 Kang, Eunsuk, U-NET, https://modulabs-biomedical.github.io/U_Net
9 Exxact Corporation, Atrous Convolutions & U-Net Architectures for Deep Learning: A Brief History, https://blog.exxactcorp.com/atrous-convolutions-u-net-architectures-for-deep-learning-a
10 Olaf Ronneberger, Philipp Fischer, Thomas Brox, "U-Net: Convolutional Networks for Biomedical Image Segmentation," MICCAI, 2015. DOI: 10.1007/978-3-319-24574-4_28
11 Caglar Firat Ozgenel, Concrete Crack Segmentation Dataset, https://data.mendeley.com/datasets/jwsn7tfbrp/1#file-52a39c5f-6914-4e26-88e7-ec81bfbc938e
12 Kim Chungyun, Evaluation Method of Classification Model, https://velog.io/@skyepodium/%EB%B6%84%EB%A5%98-%EB%AA%A8%EB%8D%B8-%ED%8F%89%EA%B0%80-%EB%B0%A9%EB%B2%95