[Back]

L. Winiwarter, G. Mandlburger, S. Schmohl, N. Pfeifer:
"Classification of ALS Point Clouds Using End‑to‑End Deep Learning";
PFG - Journal of Photogrammetry, Remote Sensing and Geoinformation Science, 87 (2019), 3; 75 - 90.

Deep learning, referring to artificial neural networks with multiple layers, is widely used for classification tasks in many disciplines
including computer vision. The most popular type is the Convolutional Neural Network (CNN), commonly applied
to 2D image data. However, CNNs are difficult to adapt to irregular data like point clouds. PointNet, on the other hand, has
enabled the derivation of features based on the geometric distribution of a set of points in nD-space utilising a neural network.
We use PointNet on multiple scales to automatically learn a representation of local neighbourhoods in an end-to-end fashion,
which is optimised for semantic labelling on 3D point clouds acquired by Airborne Laser Scanning (ALS). The results are
comparable to those using manually crafted features, suggesting a successful representation of these neighbourhoods. On the
ISPRS 3D Semantic Labelling benchmark, we achieve 80.6% overall accuracy, a mid-field result. Investigation on a bigger
dataset, namely the 2011 ALS point cloud of the federal state of Vorarlberg, shows overall accuracies of up to 95.8% over largescale
built-up areas. Lower accuracy is achieved for the separation of low vegetation and ground points, presumably because of
invalid assumptions about the distribution of classes in space, especially in high alpine regions. We conclude that the method
of the end-to-end system, allowing training on a big variety of classification problems without the need for expert knowledge
about neighbourhood features can also successfully be applied to single-point-based classification of ALS point clouds.

Semantic labelling, Machine learning, Neural networks, PointNet, Airborne laser scanning

http://dx.doi.org/10.1007/s41064-019-00073-0