A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Automatic identification and characterization of discontinuities in rock masses from 3D point clouds
Abstract The routine application of remote surveying techniques which can quickly acquire 3D digital data with high resolution, in particular digital photogrammetry, light detection and ranging (LiDAR) and unmanned aerial vehicle (UAV) for rock mass characterization has rapidly grown over the past decade. In this paper, a new method for automatic identification and interpretation of rock mass discontinuities, clustering of discontinuity sets and characterization of discontinuity orientation, persistence and spacing using 3D point clouds, is presented. The proposed method is based on a four-stage procedure consisting of: (1) normal vector calculation using the iterative reweighted plane fitting (IRPF) method, (2) discontinuity sets clustering by fast search and find of density peaks (CFSFDP) algorithm, and Fisher’s K value iterative calculation to eliminate noise points, (3) discontinuity segmentation using density-ratio based method, and discontinuity plane fitting using the random sample consensus (RANSAC) algorithm, (4) persistence and spacing calculation using the theory of analytic geometry. The method is applied to two case studies (i.e. rock slopes) and compared with the results from previous studies and from manual survey. It is concluded that the proposed method is reliable and yields a great accuracy for automatic identification of discontinuities in rock masses.
Highlights: An automatic method using machine learning algorithms for discontinuity identification and extraction is proposed. Several discontinuity parameters, namely number of sets, orientation, spacing and trace length can be obtained. Discontinuity location, best fitting plane, and 3D trace mapping can also be performed. This method is applied for two real cases and produces reliable and accuracy results.
Automatic identification and characterization of discontinuities in rock masses from 3D point clouds
Abstract The routine application of remote surveying techniques which can quickly acquire 3D digital data with high resolution, in particular digital photogrammetry, light detection and ranging (LiDAR) and unmanned aerial vehicle (UAV) for rock mass characterization has rapidly grown over the past decade. In this paper, a new method for automatic identification and interpretation of rock mass discontinuities, clustering of discontinuity sets and characterization of discontinuity orientation, persistence and spacing using 3D point clouds, is presented. The proposed method is based on a four-stage procedure consisting of: (1) normal vector calculation using the iterative reweighted plane fitting (IRPF) method, (2) discontinuity sets clustering by fast search and find of density peaks (CFSFDP) algorithm, and Fisher’s K value iterative calculation to eliminate noise points, (3) discontinuity segmentation using density-ratio based method, and discontinuity plane fitting using the random sample consensus (RANSAC) algorithm, (4) persistence and spacing calculation using the theory of analytic geometry. The method is applied to two case studies (i.e. rock slopes) and compared with the results from previous studies and from manual survey. It is concluded that the proposed method is reliable and yields a great accuracy for automatic identification of discontinuities in rock masses.
Highlights: An automatic method using machine learning algorithms for discontinuity identification and extraction is proposed. Several discontinuity parameters, namely number of sets, orientation, spacing and trace length can be obtained. Discontinuity location, best fitting plane, and 3D trace mapping can also be performed. This method is applied for two real cases and produces reliable and accuracy results.
Automatic identification and characterization of discontinuities in rock masses from 3D point clouds
Kong, Deheng (author) / Wu, Faquan (author) / Saroglou, Charalampos (author)
Engineering Geology ; 265
2019-11-29
Article (Journal)
Electronic Resource
English
3D point cloud , Rock mass , Automatic , Discontinuity , LiDAR , UAV , <italic>P</italic> , Point cloud data , <italic>x</italic>, <italic>y</italic>, <italic>z</italic> , Three dimensional coordinates of a point , <italic>N</italic> , Number of points , <italic>p</italic> <inf><italic>i</italic></inf> , The <italic>i</italic>th point at point cloud <italic>P</italic> , <italic>N</italic> <inf><italic>k</italic></inf>(<italic>p</italic> <inf><italic>i</italic></inf>) , The <italic>k</italic> nearest neighbors of a point <italic>p</italic> <inf><italic>i</italic></inf> , <italic>Pl</italic> , The iterative reweighted fitting plane , <italic>d</italic> , The distance from a point to the fitted plane , <italic>σ</italic> <inf><italic>d</italic></inf> , Distance bandwidth , <italic>σ</italic> <inf><italic>r</italic></inf> , Fitting residual bandwidth , <italic>σ</italic> <inf><italic>n</italic></inf> , Normal difference bandwidth , <italic>CM</italic> , Positive semi-definite covariance matrix , <italic>t</italic> , Number of iterations , <bold><italic>n</italic></bold> , Normal vector , <italic>θ</italic> , Dip direction (°) , <italic>δ</italic> , Dip angle (°) , <italic>l</italic>, <italic>m</italic>, <italic>n</italic> , Three components of a normal vector , <italic>Q</italic> , Angular converted value for dip direction calculation , <italic>ld</italic> , Local density of the pole data in CFSFDP algorithm , <italic>dm</italic> , The distance between pole data in CFSFDP algorithm , <italic>md</italic> , The minimum distance between pole point and another higher density pole point in CFSFDP algorithm , <italic>d</italic> <inf><italic>cf</italic></inf> , Cutoff distance in CFSFDP algorithm , <italic>α</italic> , The angular deviation from the mean orientation , <italic>K</italic> , The Fisher Constant , <italic>M</italic> , The total number of discontinuities for one set , <italic>r</italic> <inf><italic>M</italic></inf> , The mean orientation , <italic>eps</italic> , Radius of neighborhood , <italic>η</italic> , Radius of the larger neighborhood , <italic>τ</italic> , Density ratio threshold , <italic>minsize</italic> , Threshold fordiscarding small discontinuity clusters , <italic>ua</italic>,<italic>ub</italic>,<italic>uc</italic> , Three components of the unit normal vector to the fitted plane , <italic>DL</italic> , Discontinuity location , <italic>sz</italic> , The total number of one discontinuity cluster points , <italic>TL</italic> , Trace length , <italic>ed</italic> , The Euclidean distance of two points , <italic>A</italic>, <italic>B</italic>, <italic>C</italic>, <italic>D</italic> , Normal unit vector (<italic>A</italic>, <italic>B</italic>, <italic>C</italic>) and the constant parameter <italic>D</italic> in the adjacent discontinuity plane equation , <italic>SP</italic> , Spacing value of two adjacent discontinuities
| Elsevier | 2024
Rock Discontinuities Identification from 3D Point Clouds Using Artificial Neural Network
| Online Contents | 2022