Multilevel Geometric Feature Embedding in Transformer Network for ALS Point Cloud Semantic Segmentation

Effective semantic segmentation of Airborne Laser Scanning (ALS) point clouds is a crucial field of study and influences subsequent point cloud application tasks. Transformer networks have made significant progress in 2D/3D computer vision tasks, exhibiting superior performance. We propose a multilevel geometric feature embedding transformer network (MGFE-T), which aims to fully utilize the three-dimensional structural information carried by point clouds and enhance transformer performance in ALS point cloud semantic segmentation. In the encoding stage, compute the geometric features surrounding tee sampling points at each layer and embed them into the transformer workflow. To ensure that the receptive field of the self-attention mechanism and the geometric computation domain can maintain a consistent scale at each layer, we propose a fixed-radius dilated KNN (FR-DKNN) search method to address the limitation of traditional KNN search methods in considering domain radius. In the decoding stage, we aggregate prediction deviations at each level into a unified loss value, enabling multilevel supervision to improve the network's feature learning ability at different levels. The MGFE-T network can predict the class label of each point in an end-to-end manner. Experiments were conducted on three widely used benchmark datasets. The results indicate that the MGFE-T network achieves superior OA and mF1 scores on the LASDU and DFC2019 datasets and performs well on the ISPRS dataset with imbalanced classes.