터널과지하공간 (Tunnel and Underground Space)

  • 제33권6호
  • /
  • Pages.508-518
  • /
  • 2023
  • /
  • 1225-1275(pISSN)
  • /
  • 2287-1748(eISSN)
한국암반공학회 (Korean Society for Rock Mechanics and Rock Engineering)
권호 표지
DOI QR코드

DOI QR Code

터널 막장 3차원 지형모델 상에서의 불연속면 자동 매핑을 위한 딥러닝 기법 적용 방안

Deep Learning Approach for Automatic Discontinuity Mapping on 3D Model of Tunnel Face

  • 추엔 팜 (한국과학기술연합대학원대학교 지반신공간공학과) ;
  • 신휴성 (한국건설기술연구원)
  • Chuyen Pham (Dept. of Geo-Space Engineering, University of Science and Technology) ;
  • Hyu-Soung Shin (Korea Institute of Civil Engineering and Building Technology)
  • 투고 : 2023.11.22
  • 심사 : 2023.12.26
  • 발행 : 2023.12.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

이 논문은 LiDAR 스캔 또는 사진측량 기술에 의해 재구성된 3D 디지털 모델을 기반으로 터널 벽면의 불연속면을 자동으로 매핑하는 새로운 접근 방식을 제안한다. 본 제안에서는 U-Net이라 불리는 딥러닝 시맨틱 영역분할 모델을 사용하며, 터널 막장면의 3D 지형 모델에서 불연속면 영역을 식별해 낸다. 제안된 딥러닝 모델은 투영된 RGB 이미지, 면의 깊이 이미지 및 국부적인 면의 표면 속성 이미지(즉, 법선 벡터 및 곡률 이미지)를 포함한 다양한 정보를 종합 학습하여 기본 3차원 이미지에서 불연속면 영역을 효과적으로 분할한다. 이후 영역분할 결과는 면의 깊이 맵과 투영 행렬을 사용하여 3D 모델로 다시 투영시키고, 3D 공간 내에서 불연속면의 위치 및 범위를 정확하게 표현한다. 영역분할 모델의 성능은 영역 분할된 결과를 해당 지면 실측 값과 비교함으로써 평가하였으며, IoU(intersection-over-union) 값이 약 0.8 정도로 나타나 영역분할 결과의 높은 정확성을 확인하였다. 여전히 학습데이터가 제한적 이었음에도 불구하고, 제안 기법은 3D 모델의 점군 데이터를 불연속면의 유사군으로 그룹화하기 위해 전 막장면의 법선 벡터와 클러스터링과 같은 비지도 학습기반 알고리즘에만 의존하던 기존 접근 방식의 한계의 극복 가능성을 보여주었다.

This paper presents a new approach for the automatic mapping of discontinuities in a tunnel face based on its 3D digital model reconstructed by LiDAR scan or photogrammetry techniques. The main idea revolves around the identification of discontinuity areas in the 3D digital model of a tunnel face by segmenting its 2D projected images using a deep-learning semantic segmentation model called U-Net. The proposed deep learning model integrates various features including the projected RGB image, depth map image, and local surface properties-based images i.e., normal vector and curvature images to effectively segment areas of discontinuity in the images. Subsequently, the segmentation results are projected back onto the 3D model using depth maps and projection matrices to obtain an accurate representation of the location and extent of discontinuities within the 3D space. The performance of the segmentation model is evaluated by comparing the segmented results with their corresponding ground truths, which demonstrates the high accuracy of segmentation results with the intersection-over-union metric of approximately 0.8. Despite still being limited in training data, this method exhibits promising potential to address the limitations of conventional approaches, which only rely on normal vectors and unsupervised machine learning algorithms for grouping points in the 3D model into distinct sets of discontinuities.

키워드

과제정보

This research was supported by the project "Development of environmental simulator and advanced construction technologies over TRL6 in extreme conditions" and the International Collaboration Program (Project No. 20230361-001) funded by KICT.

참고문헌

  1. Chen, J., Fang, Q., Zhang, D., and Huang, H., 2023, A critical review of automated extraction of rock mass parameters using 3D point cloud data, Intelligent Transportation Infrastructure, 2. 
  2. Chen, J., Zhu, H., and Li, X., 2016, Automatic extraction of discontinuity orientation from rock mass surface 3D point cloud, Comput. Geosci., 95, 18-31.  https://doi.org/10.1016/j.cageo.2016.06.015
  3. Cignoni, P., Callieri, M., Corsini, M., Dellepiane, M., Ganovelli, F., and Ranzuglia, G. 2008. MeshLab: an open-source mesh processing tool. In: Scarano V,Chiara RD, Erra U, editors. Eurographics Italian chapter conference, The Eurographics Association, 129-136. 
  4. Daghigh, H., Tannant, D.D., Daghigh, V., Lichti, D.D., and Lindenbergh, R., 2022, A critical review of discontinuity plane extraction from 3D point cloud data of rock mass surfaces, Comput. Geosci., 169, 105241. 
  5. Kingma, D.P. and Ba, J., 2014, Adam: A Method for Stochastic Optimization, arXiv preprint arXiv: 1412.6980. 
  6. Kong, D., Wu, F., and Saroglou, C., 2020, Automatic identification and characterization of discontinuities in rock masses from 3D point clouds, Engineering Geology, 265, 105442. 
  7. Lato, M.J. and Voge, M., 2012, Automated mapping of rock discontinuities in 3D lidar and photogrammetry models, International Journal of Rock Mechanics and Mining Sciences, 54, 150-158.  https://doi.org/10.1016/j.ijrmms.2012.06.003
  8. Li, X., Chen, J., and Zhu, H., 2016, A new method for automated discontinuity trace mapping on rock mass 3D surface model, Comput. Geosci., 89, 118-131.  https://doi.org/10.1016/j.cageo.2015.12.010
  9. Liu, L., Xiao, J., and Wang, Y., 2019, Major orientation estimation-based rock surface extraction for 3D rock-mass point clouds, Remote Sens., 11, 635. 
  10. Pham, C. and Shin, H.S., 2022, 3D Tunnel Face Modelling for Discontinuities Characterization: A Comparison of Lidar and Photogrammetry Methods, Tunnel and Underground Space, 32(6), 549-557.  https://doi.org/10.7474/TUS.2022.32.6.549
  11. Riquelme, A.J., Tomas, R., Abellan, A., and Jaboyedoff, M., 2014, A new approach for semi- automatic rock mass joints recognition from 3D point clouds, Comput. Geosci., 68, 38-52.  https://doi.org/10.1016/j.cageo.2014.03.014
  12. Ronneberger, O., Fischer, P., and Brox, T., 2015, U-Net: Convolutional Networks for Biomedical Image Segmentation, MICCAI, Springer, LNCS, 9351:234-241. 
  13. Singh, S.K., Banerjee, B.P., Lato, M.J., Sammut, C., and Raval, S., 2022, Automated rock mass discontinuity set characterization using amplitude and phase decomposition of point cloud data, International Journal of Rock Mechanics and Mining Sciences, 152, 105072.