Abstract
Three methods to estimate the presence of ground surface stones from publicly available Airborne Laser Scanning (ALS) point clouds are presented. The first method approximates the local curvature by local linear multi-scale fitting, and the second method uses Discrete-Differential Gaussian curvature based on the ground surface triangulation. The third baseline method applies Laplace filtering to Digital Elevation Model (DEM) in a 2 m regular grid data. All methods produce an approximate Gaussian curvature distribution which is then vectorized and classified by logistic regression. Two training data sets consisted of 88 and 674 polygons of mass-flow deposits, respectively. The locality of the polygon samples is a sparse canopy boreal forest, where the density of ALS ground returns is sufficiently high to reveal information about terrain micro-topography. The surface stoniness of each polygon sample was categorized for supervised learning by expert observation on the site. The leave-pair-out (L2O) cross-validation of the local linear fit method results in the area under curve A U C = 0 . 74 and A U C = 0 . 85 on two data sets, respectively. This performance can be expected to suit real world applications such as detecting coarse-grained sediments for infrastructure construction. A wall-to-wall predictor based on the study was demonstrated.
Highlights
There is an increased attention towards classification of the small scale patterns of terrain surface.Recognition of micro-topography may help in arctic infrastructure planning [1], terrain trafficability prediction [2], in hydraulic modeling [3], and in detecting geomorphologic features like in [3,4], and terrain analysis and modelling.In Finland, a nationwide airborne light detection and ranging (LiDAR) mapping program has provided the means for detecting ground objects with the ground return density ρ ≈ 0.8 m−2
Both LLC and Discrete Laplace Operator (DEC) are ready to be applied to industrial purposes after prototyping implementations are upgraded to production code
Current results are bound to stoniness of mass-flow deposits what comes to teaching data, but each method should work in generic stoniness detection, if such a need arises and general teaching data sets become available
Summary
There is an increased attention towards classification of the small scale patterns of terrain surface.Recognition of micro-topography may help in arctic infrastructure planning [1], terrain trafficability prediction [2], in hydraulic modeling [3], and in detecting geomorphologic features like in [3,4], and terrain analysis and modelling.In Finland, a nationwide airborne light detection and ranging (LiDAR) mapping program has provided the means for detecting ground objects with the ground return density ρ ≈ 0.8 m−2. There is an increased attention towards classification of the small scale patterns of terrain surface. Recognition of micro-topography may help in arctic infrastructure planning [1], terrain trafficability prediction [2], in hydraulic modeling [3], and in detecting geomorphologic features like in [3,4], and terrain analysis and modelling. In Finland, a nationwide airborne light detection and ranging (LiDAR) mapping program has provided the means for detecting ground objects with the ground return density ρ ≈ 0.8 m−2. Since one needs at least one point per stone, and to define the stone radius one needs at least 4 points per stone, this leads to an absolute theoretical detection limit of stone radius rmin = 0.6...1.2 m. The real limit is naturally somewhat higher. The actual stone sizes fall into this critical range (as discussed in Section 2.2) making the stoniness detection a difficult problem
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
