대한건축학회논문집 (Journal of the Architectural Institute of Korea)

  • 제39권1호
  • /
  • Pages.313-320
  • /
  • 2023
  • /
  • 2733-6239(pISSN)
  • /
  • 2733-6247(eISSN)
대한건축학회 (Architectural Institute of Korea)
권호 표지
DOI QR코드

DOI QR Code

MEMS 라이다 센서를 활용한 심층학습 기반 조적벽체 결함 인식 기술

Deep Learning based Masonry Wall Defect Classification using a MEMS LiDAR

  • Hwang, Yeongseo (Dept. of Architecture and Civil Engineering, Chonnam National University) ;
  • Park, Gunhyung (Dept. of Architecture and Civil Engineering, Chonnam National University, Korea) ;
  • Yang, Kanghyeok (Dept. of Architecture and Civil Engineering & School of Architecture, Chonnam National University)
  • 투고 : 2022.09.23
  • 심사 : 2022.12.16
  • 발행 : 2023.01.30
⟨ 이전 논문 다음 논문 ⟩

초록

Most of the maintenance and safety inspections of buildings are performed with visual assessment of the inspector, which consumes a lot of time and cost. With the development of computer vision and digital technologies such as 3D Laser scanners, automatic defect recognition using image processing and artificial intelligence has been widely studied. Current approach is largely relying on the image obtained from the camera and the recognition performance could be varied depending on the surrounding environment. Recently, studies using 3D Laser scanner are being conducted to solve these problems. However, terrestrial laser scanners are expensive, so it is difficult to apply at the construction site. Therefore, this study proposed a method that can recognize masonry wall defects using a Microelectromechanical systems based Light Detection and Ranging sensor that having much lower price and reliable performance. This study was performed using masonry wall structures and data were collected from samples having various types of defects in a laboratory environment. Masonry wall defects were recognized using ResNet-50 and VGG16 models, which are widely used in previous studies. As a result of the classification, ResNet-50 and VGG16 achieved 98.75% and 96.88% accuracy, respectively. The results of this study can be utilized in the development of real-time defect recognition method for a masonry wall at construction sites.

키워드

과제정보

이 연구는 정부(과학기술정보통신부)의 재원으로 한국연구재단 (No. 2021R1F1A1063338) 및 국토교통부/국토교통과학기술진흥원 (과제번호: 21CTAP-C163631-01)의 지원을 받아 수행된 연구임

참고문헌

  1. Brackenbury, D., Brilakis, I., & DeJong, M. (2019). Automated defect detection for masonry arch bridges. In International Conference on Smart Infrastructure and Construction 2019 (ICSIC) Driving data-informed decision-making, 3-9.
  2. Cha, Y. J., Choi, W., & Buyukozturk, O. (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. Chaiyasarn, K., Sharma, M., Ali, L., Khan, W., & Poovarodom, N. (2018). Crack detection in historical structures based on convolutional neural network. GEOMATE Journal, 15(51), 240-251.
  4. Dais, D., Bal, I. E., Smyrou, E., & Sarhosis, V. (2021). Automatic crack classification and segmentation on masonry surfaces using convolutional neural networks and transfer learning. Automation in Construction, 125, 103606.
  5. Hallee, M. J., Napolitano, R. K., Reinhart, W. F., & Glisic, B. (2021). Crack detection in images of masonry using cnns. Sensors, 21(14), 4929.
  6. He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, 770-778.
  7. Jung, S. Y., Lee, S. K., Park, C. I., Cho, S. Y., & Yu, J. H. (2019). A method for detecting concrete cracks using deep-learning and image processing. Journal of the Architectural Institute of Korea Structure & Construction, 35(11), 163-170.
  8. Kaya, E., & Sert, E. (2020). A new 3D segmentation approach using extreme learning machine algorithm and morphological operations. Computers & Electrical Engineering, 84, 106638.
  9. Kim, A. R., Kim, D., Byun, Y. S., & Lee, S. W. (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
  10. Kim, B., Kim, G., Jin, S., & Cho, S. (2019). A comparative study on performance of deep learning models for vision-based concrete crack detection according to model types. Journal of the Korean Society of Safety, 34(6), 50-57.
  11. Kim, J., Shin, Y. S., & Min, K. W. (2018). Line laser image processing for automated crack detection of concrete structures. Journal of the Computational Structural Engineering Institute of Korea, 31(3), 147-153. https://doi.org/10.7734/COSEIK.2018.31.3.147
  12. Kim, S. M., Sohn, J. M., & Kim, D. S. (2020). A method for concrete crack detection using U-Net based image inpainting technique. Journal of the Korea Society of Computer and Information, 25(10), 35-42.
  13. Kim, T. Y., Jeon, B. O., & Lee, M. K. (2008). A Study on the Defect Characteristics of Masonry Building in Modern Age of Korea. Journal of the Architectural Institute of Korea Structure & Construction, 24(5), 117-124.
  14. Kwon, K. H. (2005). An Analysis on the Correlation between Crack Condition and Safety Grades in Masonry Buildings. Journal of the Korea institute for structural maintenance and inspection, 9(3), 101-110.
  15. Lourenco, F., & Araujo, H. (2021, February). Intel RealSense SR305, D415 and L515: Experimental Evaluation and Comparison of Depth Estimation. In VISIGRAPP (4: VISAPP), 362-369.
  16. Loverdos, D., & Sarhosis, V. (2022). Automatic image-based brick segmentation and crack detection of masonry walls using machine learning. Automation in Construction, 140, 104389.
  17. Park, Y. S. (2020). Masonry Structures Inspection & Maintenancep Guide (Focusing on masonry wall cracks). Korea Authority of Land & Infrastructure Safety, Retrieved on June 30, 2022 from http://www.kalis.or.kr
  18. Raj, T., Hanim Hashim, F., Baseri Huddin, A., Ibrahim, M. F., & Hussain, A. (2020). A survey on LiDAR scanning mechanisms. Electronics, 9(5), 741.
  19. Samy, M. P., Foong, S., Soh, G. S., & Yeo, K. S. (2016, November). Automatic optical & laser-based defect detection and classification in brick masonry walls. In 2016 IEEE Region 10 Conference (TENCON), 3521-3524.
  20. Seol, D. H., Oh, J. H., & Kim, H. J. (2020). Comparison of deep learning-based CNN models for crack detection. Journal of the Architectural Institute of Korea Structure & Construction, 36(3), 113-120.
  21. Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
  22. Syed, A. Q., Jothi, J. A. A., & Anusree, K. (2022, February). Crack identification from concrete structure images using deep transfer learning. In2022 2nd International Conference on Artificial Intelligence and Signal Processing (AISP), 1-7.
  23. Valero, E., Forster, A., Bosche, F., Wilson, L., & Leslie, A. (2016, September). Comparison of 3D Reality Capture Technologies for the Survey of Stone Walls. In Arqueologica 2.0: 8th International Congress on Archaeology, Computer Graphics, Cultural Heritage and Innovation.
  24. Valero, E., Bosche, F., & Forster, A. (2018). Automatic segmentation of 3D point clouds of rubble masonry walls, and its application to building surveying, repair and maintenance. Automation in Construction, 96, 29-39. https://doi.org/10.1016/j.autcon.2018.08.018
  25. Valero, E., Forster, A., Bosche, F., Hyslop, E., Wilson, L., & Turmel, A. (2019). Automated defect detection and classification in ashlar masonry walls using machine learning. Automation in construction, 106, 102846.