Journal of the Architectural Institute of Korea Structure & Construction (대한건축학회논문집:구조계)

Architectural Institute of Korea (대한건축학회)
권호 표지
DOI QR코드

DOI QR Code

A Method for Detecting Concrete Cracks using Deep-Learning and Image Processing

딥러닝 및 영상처리 기술을 활용한 콘크리트 균열 검출 방법

  • 정서영 (광운대학교 대학원 건축공학과) ;
  • 이슬기 (광운대학교 건축공학과) ;
  • 박찬일 (광운대학교 대학원 전자통신공학과) ;
  • 조수영 (광운대학교 대학원 전자통신공학과) ;
  • 유정호 (광운대학교 건축공학과)
  • Received : 2019.06.04
  • Accepted : 2019.11.06
  • Published : 2019.11.30
⟨ Previous Next ⟩

Abstract

Most of the current crack investigation work consists of visual inspection using simple measuring equipment such as crack scale. These methods involve the subjection of the inspector, which may lead to differences in the inspection results prepared by the inspector, and may lead to a large number of measurement errors. So, this study proposes an image-based crack detection method to enhance objectivity and efficiency of concrete crack investigation. In this study, YOLOv2 was used to determine the presence of cracks in the image information to ensure the speed and accuracy of detection for real-time analysis. In addition, we extracted shapes of cracks and calculated quantitatively, such as width and length using various image processing techniques. The results of this study will be used as a basis for the development of image-based facility defect diagnosis automation system.

Keywords

Acknowledgement

Supported by : 한국연구재단

References

  1. Byun, T., Kim, J., & Kim, H. (2006). The Recognition of Crack Detection Using Difference Image Analysis Method based on Morphology, Journal of the Korea Institute of Information and Communication Engineering, 10(1), 197-205.
  2. Cha, Y., Choi, W., & Oral, B. (2017). Deep Learning‐Based Crack Damage Detection Using Convolutional Neural Networks, Computer-Aided Civil and Infrastructure Engineering, 32(5), 361-378. https://doi.org/10.1111/mice.12263
  3. Chen, L., Jan, H., & Huang, C. (2001). Mensuration of Concrete Cracks Using Digitized Close-Range Photographs, The 22nd Asian conference of Remote Sensing, 5-9.
  4. Cho, S., Kim, B., & Lee, Y. (2018). Image-Based Concrete Crack and Spalling Detection using Deep Learning, The Magazine of the Korean Sosiety of Civil Engineers, 66(8), 92-97.
  5. Donglai, wei., Bolei, Whou., Antonio, Torralba., and William, T.Freema. (2015). "mNeuron: A Maltlab Plugin to Visualize neurons From Deep Models"
  6. Joseph, R., Santosh, Divvala., Ross, G., & Ali, F. (2016). You Only Look Once: Unified, Real-Time Object Detection, The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 779-788.
  7. Joseph, R., & Ali, F. (2017). YOLO9000: Better, Faster, Stronger, The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 1-9.
  8. Kim, A., Kim, D., Byun, Y., & Lee, S. (2018). 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. https://doi.org/10.7843/KGS.2018.34.12.145
  9. Kim, K., Cho, J., & Ahn, S. (2005). A Thechnique for Image Processing of Concrete Surface Cracks, Journal of the Korea Institute of Information and Communication Engineering, 9(7), 1575-1581.
  10. Kim, K., & Cho, J. (2010). Detection of Concrete Surface Cracks using Fuzzy Techniques, Journal of the Korea Institute of Information and Communication Engineering, 14(6), 1353-1358. https://doi.org/10.6109/jkiice.2010.14.6.1353
  11. Kim, J., & Cho, Y. (2002). Development of Crack Detection Program on Asphalt Pavement, Journal of the Korean Society Of Civil Engineers, 22(4D), 639-647.
  12. Kim, J., Jung, Y., & Rhim, H. (2017). Study on Structure Visual Inspection Technology using Drones and Image Analysis Techniques, Journal of the Korean Institute of Building Construction, 17(6), 545-557.
  13. K, Lenc., & A, Vedaldi. (2015). R-cnn minus r. arXiv preprintarXiv:1506.06981.
  14. Kim, Y. (2016). Development of Crack Recognition System for Concrete Structure Using Image Processing Method, The Journal of Korean Institute of Information Technology, 14(10), 163-168.
  15. Ko, K., & Sim, K. (2017). Trends in Object Recognition and Detection Using Deep Learning, Journal of Institute of Control, Robotics and Systems, 23(3), 17-24.
  16. Lee, B., Kim, Y., & Kim, J. (2005). Development of Image Processing for Concrete Surface Cracks by Employing Enhanced Binarization and Shape Analysis Technique, Journal of the Korea Concrete Institute, 17(3), 361-368. https://doi.org/10.4334/JKCI.2005.17.3.361
  17. Lee, J., & Kim, K. (2007). Extraction and Analysis of Crack on Concrete Surfaces Using Improved Image Processing Techniques, Proceeding of the Korea Intelligent Information Systems Society Conference, 365-372.
  18. Lee, H., Kim, J., & Jang, I. (2012). Development of Automatic Crack Detection System for Concrete Structure Using Image Processing Method, Journal of The Korea Institute for Structural Maintenance and Inspection, 16(1), 64-78. https://doi.org/10.11112/jksmi.2012.16.1.064
  19. R, B, Girshick. (2015). Fast R-CNN. CoRR, abs/1504.08083, 2015.
  20. Son, B., & Lee, K. (2017). Crack Recognition of Sewer with Low Resolution using Convolutional Neural Network(CNN) Method, Journal of the Korean Society for Advanced Composite Structures, 8(4) 58-65. https://doi.org/10.11004/kosacs.2017.8.4.058
  21. Syed, I, H., Dang, L, M., Im, S., Min, K., Nam, J., & Moon, H. (2018). Damage Detection and Classification System for Sewer Inspection using Convolutional Neural Networks based on Deep Learning, Journal of the Korea Institute of Information and Communication Engineering, 22(3), 451-457. https://doi.org/10.6109/jkiice.2018.22.3.451
  22. S, Ren., K, He., R, Girshick., & J, Sun. (2015). Faster r-cnn: Towards real-time object detection with region proposal networks. arXiv preprint arXiv:1506.01497.
  23. W. Liu, D. Anguelov, D. Erhan, C. Szegedy, & S. E. eed. (2015). SSD: single shot multibox detector. CoRR, abs/1512.02325.