3D Terrestrial LiDAR data classification of complex natural scenes using a multi-scale dimensionality criterion: applications in geomorphology

By Nicolas Brodu, Dimitri Lague. arXiv.org, 2011

612 citations recorded by the source corpus.

3D point clouds of natural environments relevant to problems in geomorphology often require classification of the data into elementary relevant classes. A typical example is the separation of riparian vegetation from ground in fluvial environments, the distinction between fresh surfaces and rockfall in cliff environments, or more generally the classification of surfaces according to their morphology. Natural surfaces are heterogeneous and their distinctive properties are seldom defined at a unique scale, prompting the use of multi-scale criteria to achieve a high degree of classification success. We have thus defined a multi-scale measure of the point cloud dimensionality around each point, which characterizes the local 3D organization. We can thus monitor how the local cloud geometry behaves across scales. We present the technique and illustrate its efficiency in separating riparian vegetation from ground and classifying a mountain stream as vegetation, rock, gravel or water surface. In these two cases, separating the vegetation from ground or other classes achieve accuracy larger than 98 %. Comparison with a single scale approach shows the superiority of the multi-scale analysis in enhancing class separability and spatial resolution. The technique is robust to missing data, shadow zones and changes in point density within the scene. The classification is fast and accurate and can account for some degree of intra-class morphological variability such as different vegetation types. A probabilistic confidence in the classification result is given at each point, allowing the user to remove the points for which the classification is uncertain. The process can be both fully automated, but also fully customized by the user including a graphical definition of the classifiers. Although developed for fully 3D data, the method can be readily applied to 2.5D airborne lidar data.

Subfields: Ecology, Environmental Engineering

View Paper: https://www.semanticscholar.org/paper/871af04fdab076aad43cbfbcdf60988f9021289c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Ecology

In Environmental Engineering

Citations in the corpus

Towards 3D lidar point cloud registration improvement using optimal neighborhood knowledge (2013, background): “In (Demantké et al., 2011 and Brodu and Lague, 2012), the multi-scale analysis of 3D lidar points, based solely on the geometrical information allows to retrieve for each point the optimal neighborhood size and the prominent behaviour of the vicinity (linear, planar, or volumetric).”
Eigen-feature analysis of weighted covariance matrices for LiDAR point cloud classification (2014, methodology): “Note that our classifications have accuracies between 90% and 95%, which is slightly lower than those from the previous studies (Antonarakis et al., 2008; Brodu and Lague, 2012) with accuracies above 95%.”
Structure from motion photogrammetry in physical geography (2016, background): “Brodu and Lague (2012) identify such points based on multi-scale dimensionality criteria.”
Analyzing High Resolution Topography for Advancing the Understanding of Mass and Energy Transfer Through Landscapes: A Review (2015, methodology): “Clearly, objects exist across a variety of scales in HRT, and so segmentation often requires a multi-scale analysis (Hay et al., 2001; Burnett and Blaschke, 2003; Hay et al., 2003; Schmidt and Andrew, 2005; Brodu and Lague, 2012).”
Accurate 3D comparison of complex topography with terrestrial laser scanner: Application to the Rangitikei canyon (N-Z) (2013, methodology): “14 Prior to point-cloud comparison, the vegetation is automatically removed using a multiscale dimensionality classification algorithm (Brodu and Lague, 2012) (fig.”
FAST SEMANTIC SEGMENTATION OF 3D POINT CLOUDS WITH STRONGLY VARYING DENSITY (2016, methodology): “To further accelerate processing it has been proposed to approximate larger neighborhoods, by ﬁrst downsampling the point cloud and then picking a proportionally smaller number k of nearest neighbors as representatives (Brodu and Lague, 2012).”