Deep Learning Approach for Automatic Discontinuity Mapping on 3D Model of Tunnel Face
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
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 tech- niques. 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 repre- sentation 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 conven- tional approaches, which only rely on normal vectors and unsupervised machine learning algorithms for grouping points in the 3D model into distinct sets of discontinuities.
Abstract
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 tech- niques. 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 repre- sentation 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 conven- tional approaches, which only rely on normal vectors and unsupervised machine learning algorithms for grouping points in the 3D model into distinct sets of discontinuities.
참고문헌 (13)
- Chen, J., "A critical review of automated extraction of rock mass parameters using 3D point cloud data", Intelligent Transportation Infrastructure, 2 (2023)
- Chen, J., "Automatic extraction of discontinuity orientation from rock mass surface 3D point cloud", Comput. Geosci, 95, pp.18~31 (2016)
- Cignoni, P., "MeshLab: an open-source mesh processing tool", Eurographics Italian chapter conference, pp.129~136 (2008), The Eurographics Association
- Daghigh, H., "A critical review of discontinuity plane extraction from 3D point cloud data of rock mass surfaces", Comput. Geosci, 169, pp.105241~ (2022)
- Kingma, D. P., "Adam : A Method for Stochastic Optimization", arXiv preprint arXiv: 1412.6980, ~ (2014)
- Kong, D., "Automatic identification and characterization of discontinuities in rock masses from 3D point clouds", Engineering Geology, 265, pp.105442~ (2020)
- Lato, M. J., "Automated mapping of rock discontinuities in 3D lidar and photogrammetry models", International Journal of Rock Mechanics and Mining Sciences, 54, pp.150~158 (2012)
- Li, X., "A new method for automated discontinuity trace mapping on rock mass 3D surface model", Comput. Geosci, 89, pp.118~131 (2016)
- Liu, L., "Major orientation estimation-based rock surface extraction for 3D rock-mass point clouds", Remote Sens, 11, pp.635~ (2019)
- 추엔 팜, "3D Tunnel Face Modelling for Discontinuities Characterization: A Comparison of Lidar and Photogrammetry Methods", 터널과 지하공간, 32(6), pp.549~557 (2022), 한국암반공학회
- Riquelme, A. J., "A new approach for semi-automatic rock mass joints recognition from 3D point clouds", Comput. Geosci, 68, pp.38~52 (2014)
- Ronneberger, O., "U-Net: Convolutional Networks for Biomedical Image Segmentation", MICCAI, pp.234~241 (2015), Springer
- Singh, S. K., "Automated rock mass discontinuity set characterization using amplitude and phase decomposition of point cloud data", International Journal of Rock Mechanics and Mining Sciences, 152, pp.105072~ (2022)