Journal of the Korea institute for structural maintenance and inspection (한국구조물진단유지관리공학회 논문집)

Korea Institute for Structural Maintenance Inspection (한국구조물진단유지관리공학회)
권호 표지
DOI QR코드

DOI QR Code

Estimation of Concrete Porosity Using Image Segmentation Method

영상 분할기법을 활용한 콘크리트의 공극률 평가

  • 정현준 (서울시립대학교, 건축공학과 스마트시티융합전공) ;
  • 정호성 (서울시립대학교, 건축공학과 스마트시티융합전공) ;
  • 김재현 (서울시립대학교, 건축공학과) ;
  • 김강수 (서울시립대학교, 건축공학과 스마트시티융합전공)
  • Received : 2022.11.03
  • Accepted : 2023.01.09
  • Published : 2023.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

In this study, an image segmentation model that can evaluate surface porosity based on concrete surface images was derived. Three types of concrete specimens with different water-cement ratios (w/c = 54, 35, and 30%) were prepared, and 2,729 surface images were obtained using an optical microscope. Benchmarking tests, parameter optimization, and final model derivation were performed using the surface images, and an image segmentation model with 97% verification accuracy was obtained. The model was verified by comparing the porosity obtained from the model and X-Ray Microscope (XRM). The model provided similar porosity to that of XRM for the specimens with a high water-cement ratio, but tended to give lower porosity for specimens with a low water-cement ratio.

이 연구에서는 콘크리트 표면 이미지를 활용하여 표면공극률을 평가할 수 있는 영상 분할모델을 도출하였다. 물-시멘트비가 다른 3종류의 콘크리트 실험체 (w/c = 54, 35, 및 30%) 가 제작되었으며, 광학현미경을 활용하여 2,729장의 표면 이미지를 취득하였다. 공극이 마스킹 된 표면 이미지 를 활용하여 벤치마킹 테스트, 매개변수 최적화, 최종모델 도출이 실시되었으며, 97%의 검증정확도를 나타내는 영상 분할 모델을 도출할 수 있었다. 영상 분할모델 및 X-Ray Microscope (XRM)을 통해 얻은 공극률을 비교하여 모델을 검증하였으며, 물시멘트비가 높은 시편에 대해선 모델과 XRM이 평가한 공극률이 유사하였고, 물시멘트비가 낮은 시편에 대해서는 모델이 XRM보다 공극률을 낮게 평가하는 경향을 나타내었다.

Keywords

Acknowledgement

이 논문은 2022년도 정부(과학기술정보통신부)의 재원으로 한국연구재단의 지원을 받아 수행된 연구임(No. 2019R1A2C2086388).

References

  1. Ministry of Land, Infrastructure and Transport. (2022), Guidelines for safety and maintenance of infrastructures, Korea Ministry of Government Legislation. https://www.law.go.kr/
  2. Chang, C. F., and Chen, J. W. (2006). The experimental investigation of concrete carbonation depth, Cement and Concrete Research, 36(9), 1760-1767. https://doi.org/10.1016/j.cemconres.2004.07.025
  3. KS F 2385. (2018). Permeable asphalt mixtures, Korea Standards Association. https://e-ks.kr/streamdocs/view/sd;streamdocsId=7 2059199200454467
  4. Lu, S., Landis, E. N., and Keane, D. T. (2006). X-ray microtomographic studies of pore structure and permeability in Portland cement concrete, Materials and Structures, 39(6), 611-620. https://doi.org/10.1617/s11527-006-9099-7
  5. Torres-Luque, M., Bastidas-Arteaga, E., Schoefs, F., SanchezSilva, M., and Osma, J. F. (2014). Non-destructive methods for measuring chloride ingress into concrete: State-of-the-art and future challenges, Construction and Building Materials, 68, 68-81. https://doi.org/10.1016/j.conbuildmat.2014.06.009
  6. Hofmarcher, M., Unterthiner, T., Arjona-Medina, J., Klambauer, G., Hochreiter, S., & Nessler, B. (2019). Visual scene understanding for autonomous driving using semantic segmentation, Explainable AI: Interpreting, Explaining and Visualizing Deep Learning, 285-296.
  7. Wang, G., Li, W., Zuluaga, M. A., Pratt, R., Patel, P. A., Aertsen, M., ... & Vercauteren, T. (2018). Interactive medical image segmentation using deep learning with image-specific fine tuning, IEEE Transactions on Medical Imaging, 37(7), 1562-1573. https://doi.org/10.1109/tmi.2018.2791721
  8. Dogan, G., Arslan, M. H., and Ceylan, M. (2017), Concrete compressive strength detection using image processing based new test method, Measurement, 109, 137-148. https://doi.org/10.1016/j.measurement.2017.05.051
  9. Jang, Y., Ahn, Y., and Kim, H. Y. (2019). Estimating compressive strength of concrete using deep convolutional neural networks with digital microscope images, Journal of Computing in Civil Engineering, 33(3), 04019018.
  10. Yang, H., Jiao, S. J., and Yin, F. D. (2020). Multilabel Image Classification Based Fresh Concrete Mix Proportion Monitoring Using Improved Convolutional Neural Network, Sensors, 20(16), 4638.
  11. Dung, C. V. (2019). Autonomous concrete crack detection using deep fully convolutional neural network, Automation in Construction, 99, 52-58. https://doi.org/10.1016/j.autcon.2018.11.028
  12. Otsu, N. (1979). A threshold selection method from gray-level histograms, IEEE Transactions on Systems, Man, and Cybernetics, 9(1), 62-66. https://doi.org/10.1109/TSMC.1979.4310076
  13. Dhanachandra, N., Manglem, K., and Chanu, Y. J. (2015). Image segmentation using K-means clustering algorithm and subtractive clustering algorithm, Procedia Computer Science, 54, 764-771. https://doi.org/10.1016/j.procs.2015.06.090
  14. Long, J., Shelhamer, E., and Darrell, T. (2015). Fully convolutional networks for semantic segmentation, Proceedings of the IEEE conference on computer vision and pattern recognition, 3431-3440.
  15. Ronneberger, O., Fischer, P., and Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation, International Conference on Medical image computing and computer-assisted intervention, Springer, Berlin, 234-241.
  16. Chen, L. C., Papandreou, G., Kokkinos, I., Murphy, K., and Yuille, A. L. (2017). Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs, IEEE transactions on pattern analysis and machine intelligence, 40(4), 834-848. https://doi.org/10.1109/TPAMI.2017.2699184
  17. Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., ... and Adam, H. (2017). Mobilenets: Efficient convolutional neural networks for mobile vision applications, arXiv preprint arXiv, 1704.04861.
  18. Ahn, J., Lee, Y., Vaidya, S., Kim, J. H., & Lee, S. W. (2013). Estimation the porosity of pervious concretes based on X-Ray CT and submerged weight, Journal of the Korean Society of Hazard Mitigation, 13(4), 77-82. https://doi.org/10.9798/KOSHAM.2013.13.4.077
  19. Kumar, R., and Bhattacharjee, B. (2003). Porosity, pore size distribution and in situ strength of concrete, Cement and Concrete Research, 33(1), 155-164. https://doi.org/10.1016/S0008-8846(02)00942-0
  20. Nitto. Concrete tester and surveyor(User manual). (2009). Nitto, Osaka, Japan.
  21. KS F 2405. (2022). Test method for compressive strength of concrete, Korea Standards Association. https://e-ks.kr/streamdocs/ vIew/sd;streamdocsId=7205926579 6199707
  22. Liashchynskyi, P., and Liashchynskyi, P. (2019). Grid search, random search, genetic algorithm: A big comparison for NAS, arXiv preprint arXiv, 1912.06059.