한국공간구조학회논문집 (Journal of Korean Association for Spatial Structures)

  • 제22권2호
  • /
  • Pages.19-27
  • /
  • 2022
  • /
  • 1598-4095(pISSN)
  • /
  • 2287-7401(eISSN)
한국공간구조학회 (Korean Association for Spatial Structures)
권호 표지
DOI QR코드

DOI QR Code

합성곱 신경망을 이용한 정사사진 기반 균열 탐지 기법

Crack Detection Technology Based on Ortho-image Using Convolutional Neural Network

  • 장아름 (고려대학교 건축사회환경공학과) ;
  • 정상기 (고려대학교 건축사회환경공학과) ;
  • 박진한 (현대엔지니어링(주) 스마트기술센터 스마트 컨스트럭션실) ;
  • 강창훈 (현대엔지니어링(주) 스마트기술센터 스마트 컨스트럭션실) ;
  • 주영규 (고려대학교 건축사회환경공학부)
  • Jang, Arum (School of Civil, Environmental, and Architectural Engineering, Korea University) ;
  • Jeong, Sanggi (School of Civil, Environmental, and Architectural Engineering, Korea University) ;
  • Park, Jinhan (Smart Construction team, Smart Technology Center, Hyundai Engineering Co., Ltd.) ;
  • , Kang Chang-hoon (Smart Construction team, Smart Technology Center, Hyundai Engineering Co., Ltd.) ;
  • Ju, Young K. (School of Civil, Environmental, and Architectural Engineering, Korea University)
  • 투고 : 2022.05.26
  • 심사 : 2022.06.13
  • 발행 : 2022.06.15
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Visual inspection methods have limitations, such as reflecting the subjective opinions of workers. Moreover, additional equipment is required when inspecting the high-rise buildings because the height is limited during the inspection. Various methods have been studied to detect concrete cracks due to the disadvantage of existing visual inspection. In this study, a crack detection technology was proposed, and the technology was objectively and accurately through AI. In this study, an efficient method was proposed that automatically detects concrete cracks by using a Convolutional Neural Network(CNN) with the Orthomosaic image, modeled with the help of UAV. The concrete cracks were predicted by three different CNN models: AlexNet, ResNet50, and ResNeXt. The models were verified by accuracy, recall, and F1 Score. The ResNeXt model had the high performance among the three models. Also, this study confirmed the reliability of the model designed by applying it to the experiment.

키워드

과제정보

이 논문은 2021년도 현대엔지니어링(주) 스마트기술센터와 한국연구재단의 지원으로 수행되었습니다. (No. NRF-2020R1A2C3005687, 2021R1A5A1032433)

참고문헌

  1. El Masri, Y., & Rakha, T., "A scoping review of non-destructive testing (NDT) techniques in building performance diagnostic inspections", Construction and Building Materials, Vol.265, 2020, doi: 10.1016/j.conbuildmat.2020.120542
  2. Albeaino, G., Gheisari, M., & Franz, B. W., "A systematic review of unmanned aerial vehicle application areas and technologies in the AEC domain", J. Inf. Technol. Constr., Vol.24 pp.381-405, 2019.
  3. Bae, J., Lee, J., Jang, A., Ju, Y. K., & Park, M. J., "SMART SKY Eye system for preliminary structural safety assessment of buildings using unmanned aerial vehicles", Sensors, Vol.22, No.7, 2022, doi: 10.3390/s22072762
  4. Duarte, D., Nex, F., Kerle, N., & Vosselman, G., "Towards a more efficient detection of earthquake induced facade damages using oblique UAV imagery", The International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol.42, pp.93-100, 2017, doi: 10.5194/isprs-archives-XLII-2-W6-93-2017
  5. Nex, F., Duarte, D., Steenbeek, A., & Kerle, N., "Towards real-time building damage mapping with low-cost UAV solutions", Remote sensing, Vol11, No.3, 2019, doi:10.3390/rs11030287
  6. Kerle, N., Nex, F., Duarte, D., & Vetrivel, A., "UAV-based structural damage mapping-Results from 6 years of research in two European projects. The International Archives of Photogrammetry" Remote Sensing and Spatial Information Sciences, Vol.42, pp.187-194, 2019.
  7. Kim, I. H., Jeon, H., Baek, S. C., Hong, W. H., & Jung, H. J. (2018). "Application of crack identification techniques for an aging concrete bridge inspection using an unmanned aerial vehicle", Sensors, Vol.18, No.6, 2018, doi: 10.3390/s18061881
  8. Jiang, S., & Zhang, J., "Real-time crack assessment using deep neural networks with wall-climbing unmanned aerial system", Computer-Aided Civil and Infrastructure Engineering, Vol.35, No.6, pp.549-564, 2020, doi: 10.1111/mice.12519
  9. Munawar, H. S., Ullah, F., Heravi, A., Thaheem, M. J., & Maqsoom, A., "Inspecting Buildings Using Drones and Computer Vision: A Machine Learning Approach to Detect Cracks and Damages", Drones, Vol.6 No.1, 2022, doi: /10.3390/drones6010005
  10. Caglar, F. O., & Ozgenel, R., "Concrete crack images for classification", Mendeley Data, Version.2, 2019, doi: 10.17632/5y9wdsg2zt.2
  11. Shorten, C., & Khoshgoftaar, T. M., "A survey on image data augmentation for deep learning", Journal of big data, Vol.6, No.1, pp.1-48, 2019, doi: 10.1186/s40537-019-0197-0
  12. Dhillon, A., & Verma, G. K., "Convolutional neural network: a review of models, methodologies and applications to object detection", Progress in Artificial Intelligence, Vol.9, No.2, pp.85-112, 2020, doi: 10.1007/s13748-019-00203-0
  13. Krizhevsky, A., Sutskever, I., & Hinton, G. E., "Imagenet classification with deep convolutional neural networks", Advances in neural information processing systems, Vol.25, 2012
  14. He, K., Zhang, X., Ren, S., & Sun, J. "Deep residual learning for image recognition", In Proceedings of the IEEE conference on computer vision and pattern recognition, pp.770-778, 2016, doi: 10.1109/CVPR.2016.90
  15. Xie, S., Girshick, R., Dollar, P., Tu, Z., & He, K., "Aggregated residual transformations for deep neural networks", In Proceedings of the IEEE conference on computer vision and pattern recognition, pp.1492-1500, 2017, doi: 10.48550/arXiv.1611.05431