A geometry-attentional network for ALS point cloud classification

• Published in: ISPRS journal of photogrammetry and remote sensing Vol. 164; pp. 26 - 40
• Main Authors: Li, Wuzhao, Wang, Fu-Dong, Xia, Gui-Song
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.06.2020
• Subjects: ALS Point clouds; data collection; Deep learning; forests; Geometry-attentional network; lidar; monitoring; photogrammetry; remote sensing; Semantic labelling; surveys; urban development; Deep learning; Semantic labelling; ALS Point clouds; Geometry-attentional network
• ISSN: 0924-2716; 1872-8235
• DOI: 10.1016/j.isprsjprs.2020.03.016

[Display omitted] Airborne Laser Scanning (ALS) point cloud classification is a critical task in remote sensing and photogrammetry communities, which can be widely utilized in urban management, powerline surveying and forest monitoring, etc. In particular, the characteristics of ALS point clouds are distinctive in three aspects, (1) numerous geometric instances (e.g. tracts of roofs); (2) extreme scale variations between different categories (e.g. car v.s. roof); (3) discrepancy distribution along the elevation, which should be specifically focused on for ALS point cloud classification. In this paper, we propose a geometry-attentional network consisting of geometry-aware convolution, dense hierarchical architecture and elevation-attention module to embed the three characteristics effectively, which can be trained in an end-to-end manner. Evaluated on the ISPRS Vaihingen 3D Semantic Labeling benchmark, our method achieves the state-of-the-art performance in terms of average F1 score and overall accuracy (OA). Additionally, without retraining, our model trained on the above Vaihingen 3D dataset can also achieve a better result on the dataset of 2019 IEEE GRSS Data Fusion Contest 3D point cloud classification challenge (DFC 3D) than the baseline (i.e. PointSIFT), which verifies the stronger generalization ability of our model.