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

  • 제26권6호
  • /
  • Pages.157-166
  • /
  • 2022
  • /
  • 2234-6937(pISSN)
  • /
  • 2287-6979(eISSN)
한국구조물진단유지관리공학회 (Korea Institute for Structural Maintenance Inspection)
권호 표지
DOI QR코드

DOI QR Code

360도 카메라 기반 건설현장 철근 배근 정보 원격 계측 기법 개발

Development of Remote Measurement Method for Reinforcement Information in Construction Field Using 360 Degrees Camera

  • 투고 : 2022.10.21
  • 심사 : 2022.11.15
  • 발행 : 2022.12.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

철근 콘크리트 구조 건설현장에서 육안 검사 방식으로 수행되는 현재 단계의 구조감리는 그 필요성에 비하여 매우 노동 집약적이기에 현실적으로 현장의 모든 상황을 파악하기에 제한적이며, 검사자의 주관성도 배제될 수 없다. 따라서 본 연구는 철근을 대상으로 한 구조감리의 효율성 개선을 위해 360° 카메라를 통해 수집한 RGB 및 Depth 데이터 기반 3D model을 이용하여 배근 간격을 도출하고 실측값과의 비교를 통해 정확도를 검증하였다. 소규모 현장(약 265 m2)의 12개 지점에 대해 계측을 수행하였으며, 지점당 스캔시간은 약 20초, 이동 및 설치시간을 포함한 총 계측 시간은 약 15분이 소요되었다. 계측된 데이터는 SLAM 알고리즘을 통하여 RGB-based 3D model과 3D point cloud model을 생성하였으며, 각각의 모델에서의 계측값을 실측값과 비교하여 정확도 검증을 진행하였다. RGB-based 3D model과 3D point cloud model은 각각 10mm, 0.1mm의 최소분해능을 갖으며, 각 모델로부터 계측된 철근의 배근 간격 은 의 오차는 최대 28.4%, 최소 3.1% (RGB-based 3D model) 최대 10.8%, 최소 0.3% (3D point cloud model)로 확인되었다. 본 연구를 토대로 추후 자동화 기반의 원격구조 감리 기술개발을 통하여 현장적용 및 분석의 효율성을 증대시키고자 한다.

Structural supervision on the construction site has been performed based on visual inspection, which is highly labor-intensive and subjective. In this study, the remote technique was developed to improve the efficiency of the measurements on rebar spacing using a 360° camera and reconstructed 3D models. The proposed method was verified by measuring the spacings in reinforced concrete structure, where the twelve locations in the construction site (265 m2) were scanned within 20 seconds per location and a total of 15 minutes was taken. SLAM, consisting of SIFT, RANSAC, and General framework graph optimization algorithms, produces RGB-based 3D and 3D point cloud models, respectively. The minimum resolution of the 3D point cloud was 0.1mm while that of the RGB-based 3D model was 10 mm. Based on the results from both 3D models, the measurement error was from 10.8% to 0.3% in the 3D point cloud and from 28.4% to 3.1% in the RGB-based 3D model. The results demonstrate that the proposed method has great potential for remote structural supervision with respect to its accuracy and objectivity.

키워드

과제정보

본 연구는 국토교통부 디지털 기반 건축시공 및 안전감리기술개발 사업(1615012983)과 2021년도 한국연구재단에서 지원하는 기초연구실(No. 2021R1A4A3030117)의 연구비 지원 의해 수행되었습니다.

참고문헌

  1. Park, H. S. (2021), Land and Transformation, Construction Transportation Journal, Seoul.
  2. Kim, J. C., Shin, S. H., and Oh, S. H. (2019), Damage Investigation of Pilotis Structures and Analysis of Damage Causes by Pohang Earthquake, Journal of the Architectural Institute of Korea Structure & Construction, AIK., 35(3), 3-10. https://doi.org/10.5659/JAIK_SC.2019.35.3.3
  3. ANCnews. (2018), Available at: http://www.ancnews.kr/news/articleView.html?idxno=6403
  4. Zhang, D., Xie, Z., and Wang, C. (2008), Bar section image enhancement and positioning method in on-line steel bar counting and automatic separating system, 2008 Congress on Image and Signal Processing, IEEE, 2, 319-323.
  5. Ying, X., Wei, X., Pei-xin, Y., Qing-da, H., and Chang-hai, C. (2010), Research on an Automatic Counting Method for Steel Bars' Image, 2010 International Conference on Electrical and Control Engineering, IEEE, 1644-1647.
  6. Fan, Z., Lu, J., Qiu, B., Jiang, T., An, K., Josephraj, A. N., and Wei, C. (2019), Automated steel bar counting and center localization with convolutional neural networks, arXiv preprint arXiv, 1906.00891.
  7. Yang, H., and Fu, C. (2019), Quantity Detection of Steel Bars Based on Deep Learning, Open Access Library Journal, OALib, 6(10), 1-9.
  8. Zhu, Y., Tang, C., Liu, H., and Huang, P. (2020), End-face localization and segmentation of steel bar based on convolution neural network, Journal of IEEE Access, IEEE, 8, 74679-74690. https://doi.org/10.1109/ACCESS.2020.2989300
  9. Li, Y., Lu, Y., and Chen, J. (2021), A deep learning approach for real-time rebar counting on the construction site based on YOLOv3 detector, Automation in Construction, Elsevier, 124, 103602. https://doi.org/10.1016/j.autcon.2021.103602
  10. Shin, Y., Heo, S., Han, S., Kim, J., and Na, S. (2021), An Image-Based Steel Rebar Size Estimation and Counting Method Using a Convolutional Neural Network Combined with Homography, Buildings, MDPI, 11(10), 463. https://doi.org/10.3390/buildings11100463
  11. Zhang, J., Mo, J., Xu, H., and Liu, Z. (2020), A semantic segmentation method for exposed rebar on dam concrete based on Unet, Journal of Physics, IOP, 1651, 012169
  12. Yuan, X., Smith, A., Sarlo, R., Lippitt, C. D., and Moreu, F. (2021), Automatic evaluation of rebar spacing using LiDAR data. Automation in Construction, Elsevier 131, 103890. https://doi.org/10.1016/j.autcon.2021.103890
  13. Kardovskyi, Y., and Moon, S. (2021). Artificial intelligence quality inspection of steel bars installation by integrating mask R-CNN and stereo vision. Automation in Construction, Elsevier, 130, 103850. https://doi.org/10.1016/j.autcon.2021.103850
  14. KD S 3504. (2021), Steel bars for concrete reinforcement.
  15. Pulcrano, M., et al. (2019), 3D cameras acquisitions for the documentation of cultural heritage, Remote Sensing and Spatial Information Sciences, ISPRS, 42, 639-646.
  16. Kang, I, S., et al. (2017), Distortion in VR 360 degree panoramic image, Proceedings of the Korean Society of Broadcast Engineers Conference, Seoul, 194-196.
  17. Matterport. (2017), Available at: https://matterport.com/
  18. Angeli, Adrien, et al. (2008), Real-time visual loop-closure detection, 2008 IEEE international conference on robotics and automation, IEEE, 1842-1847.
  19. Shi, G., Xu, X., and Dai, Y. (2013), SIFT feature point matching based on improved RANSAC algorithm, In 2013 5th International Conference on Intelligent Human-Machine Systems and Cybernetics, IEEE, 474-477.
  20. Kummerle, Rainer, et al. (2011), g2o: A general framework for graph optimization, 2011 IEEE International Conference on Robotics and Automation. IEEE, 3607-3613.
  21. Grisetti, Giorgio, et al. (2010), A tutorial on graph-based SLAM, IEEE Intelligent Transportation Systems Magazine, IEEE, 2(4) 31-43. https://doi.org/10.1109/MITS.2010.939925
  22. Gupta, M., Yin, Q., and Nayar, S. K. (2013), Structured light in sunlight, Proceedings of the IEEE International Conference on Computer Vision, 545-552.
  23. Tareen, S. A. K., and Saleem, Z. (2018), A comparative analysis of sift, surf, kaze, akaze, orb, and brisk, International conference on computing, mathematics and engineering technologies (iCoMET), IEEE, 1-10.