Abstract
The airborne LiDAR point cloud has its own characteristics, however, the classification method always fails to capture these characteristics. In this paper, a classification method named GOGCN was designed that adopts a U-Net network structure and uses a directionally constrained nearest neighbourhood search during down-sampling to generate the directionally aware feature. The point cloud geometric structure is obtained through geometry-aware information extraction, and then a graph attention convolution is utilised to learn the most representative features. A comparative experiment on GML(B) dataset and one engineering dataset demonstrated that GOGCN network have well performance and can be widely used in classification.
Disclosure statement
No potential conflict of interest was reported by the author(s).
Data availability statement
The GML (B) dataset URLs are available from https://github.com/bwf124565/data. The engineering datasets generated during the current study are available from the corresponding author on reasonable request.
Additional information
Funding
Notes on contributors
Yang Chen
Yang Chen is a lecturer in the School of Information Technology at the Suzhou Institute of Trade & Commerce, China; his research involves airborne LiDAR point cloud processing.
Jianzhou Li
Jianzhou Li is an engineer at Changjiang River Scientic Research Institute, China, him primary research focuses on engineering measurement data processing.
Yin Xing
Yin Xing is a lecture in the School of Geography Science and Geomatics Engineering at Suzhou University of Science and Technology, China; her research expertise involves deformation monitoring.
Xiao Li
Xiao Li is a lecturer in the School of Information Technology at the Suzhou Institute of Trade & Commerce, China. Her research involves multi-source data fusion and processing.
Lili Luo
Lili Luo is a lecturer in the School of Information Technology at the Suzhou Institute of Trade & Commerce, China. His research involves Remote Sensing data processing.