LGENet: Local and Global Encoder Network for Semantic Segmentation of Airborne Laser Scanning Point Clouds

TL;DR

LGENet is a novel neural network architecture that combines local and global feature extraction techniques, including 2D/3D convolutions, segment-based context encoding, and attention mechanisms, to improve semantic segmentation of airborne laser scanning point clouds.

Contribution

The paper introduces LGENet, a new model integrating local and global encoders with attention for enhanced ALS point cloud segmentation, outperforming existing methods.

Findings

Achieved state-of-the-art accuracy on ISPRS benchmark dataset.

Attained high F1 scores on DCF2019 dataset.

Effectively models local geometry and global context.

Abstract

Interpretation of Airborne Laser Scanning (ALS) point clouds is a critical procedure for producing various geo-information products like 3D city models, digital terrain models and land use maps. In this paper, we present a local and global encoder network (LGENet) for semantic segmentation of ALS point clouds. Adapting the KPConv network, we first extract features by both 2D and 3D point convolutions to allow the network to learn more representative local geometry. Then global encoders are used in the network to exploit contextual information at the object and point level. We design a segment-based Edge Conditioned Convolution to encode the global context between segments. We apply a spatial-channel attention module at the end of the network, which not only captures the global interdependencies between points but also models interactions between channels. We evaluate our method on two ALS datasets namely, the ISPRS benchmark dataset and DCF2019 dataset. For the ISPRS benchmark dataset, our model achieves state-of-the-art results with an overall accuracy of 0.845 and an average F1 score of 0.737. With regards to the DFC2019 dataset, our proposed network achieves an overall accuracy of 0.984 and an average F1 score of 0.834.