An Analysis of Ground-Point Classifiers for Terrestrial LiDAR

Abstract

Previous literature has compared the performance of existing ground point classification (GPC) techniques on airborne LiDAR (ALS) data (LiDAR—light detection and ranging); however, their performance when applied to terrestrial LiDAR (TLS) data has not yet been addressed. This research tested the classification accuracy of five openly-available GPC algorithms on seven TLS datasets: Zhang et al.’s inverted cloth simulation (CSF), Kraus and Pfeiffer’s hierarchical weighted robust interpolation classifier (HWRI), Axelsson’s progressive TIN densification filter (TIN), Evans and Hudak’s multiscale curvature classification (MCC), and Vosselman’s modified slope-based filter (MSBF). Classification performance was analyzed using the kappa index of agreement (KIA) and rasterized spatial distribution of classification accuracy datasets generated through comparisons with manually classified reference datasets. The results identified a decrease in classification accuracy for the CSF and HWRI classification of low vegetation, for the HWRI and MCC classifications of variably sloped terrain, for the HWRI and TIN classifications of low outlier points, and for the TIN and MSBF classifications of off-terrain (OT) points without any ground points beneath. Additionally, the results show that while no single algorithm was suitable for use on all datasets containing varying terrain characteristics and OT object types, in general, a mathematical-morphology/slope-based method outperformed other methods, reporting a kappa score of 0.902.

Assessment of Stem Volume on Plots Using Terrestrial Laser Scanner: A Precision Forestry Application

“…A case from Guelph, Canada illustrated the performance of several ground-point classification algorithms using different features of interest (e.g., low vegetation, high vegetation). Interestingly, the cloth simulation filter (CSF) algorithm had the highest accuracy for high vegetation (forest type), producing a kappa of 0.844 [ 28 ]. In another study, Corte et al [ 29 ] classified ground and off-ground points using the progressive TIN densification filtering technique available in LAStools for generating a DTM and digital surface model (DSM); they used a resolution of 0.5 m to extract total tree height.…”

An Analytic Model for Negative Obstacle Detection with Lidar and Numerical Validation Using Physics-Based Simulation

“…More recently, Nakano et al [ 9 ], Ravi et al [ 17 ] and Péntek et al [ 18 ] have performed fundamental analysis of lidar performance for various detection tasks, while Roberts et al [ 19 ], Azevedo et al [ 20 ] and Gilhuly and Smith [ 21 ] investigated the capability of UAV-mounted lidar in classifying ground points, detecting power lines, and terrain mapping, respectively. Additionally, Kandath et al [ 22 ] have shown the viability of incorporating sensor information from a low-flying UAV into UGV path planning algorithms.…”

Analysis of Filtering Techniques for Investigating Landslide-Induced Topographic Changes in the Oetz Valley (Tyrol, Austria)

“…The following formulas correspond to the performance metrics (e.g. Xia and Wang, 2017;Roberts et al, 2019) that were calculated from a confusion matrix of classified ground and non-ground points (abbreviations refer to Table 1):…”

“…Extracting the points that represent the terrain in a 3D point cloud has a long tradition (e.g. Kraus and Pfeifer, 1998) and a variety of techniques and tools have been proposed and evaluated to achieve this (Sithole and Vosselman, 2004;Chen et al, 2017;Roberts et al, 2019). The general principle of terrain filtering is to select those points which represent the bare earth and remove objects in the intervening space.…”

“…In general, surface-based filters tend to out-perform other techniques but the complexity of the landscape ultimately determines the accuracy of the bare-earth extraction (Sithole and Vosselman, 2004). However, recent reviews on the subject have challenged this view (Chen et al, 2017;Roberts et al, 2019), calling instead for a multi-method approach to filtering. For example, the popular Triangular Irregular Network (TIN)-based densification method (Axelsson, 2000) performs well in steep terrain but is less accurate when the surface has many sudden discontinuities (Chen et al, 2017).…”