Region-based Edge Convolutions with Geometric Attributes for the Semantic Segmentation of Large-scale 3D Point Clouds

In this article, we present a semantic segmentation framework for large-scale 3-D point clouds with high spatial resolution. For such data with huge amounts of points, the classification of each individual 3-D point is an intractable task. Instead, we propose to segment the scene into meaningful regions as a first step. Afterward, we classify these segments using a combination of PointNet and geometric deep learning. This two-step approach resembles object-based image analysis. As an additional novelty, we apply surface normalization techniques and enrich features with geometric attributes. Our experiments show the potential of this approach for a variety of outdoor scene analysis tasks. In particular, we are able to reach 89.6% overall accuracy and 64.4% average intersection over union (IoU) in the Semantic3D benchmark. Furthermore, we achieve 66.7% average IoU on Paris-Lille-3D. We also successfully apply our approach to the automatic semantic analysis of forestry data.