Tree Species Classfifcation Using Deep Learning Based 3d Point Cloud Transformer on Airborne Lidar Data
- Resource Type
- Conference
- Authors
- Wang, Lanying; Lu, Dening; Tan, Weikai; Chen, Yiping; Li, Jonathan
- Source
- IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium Geoscience and Remote Sensing Symposium, IGARSS 2023 - 2023 IEEE International. :974-977 Jul, 2023
- Subject
- Aerospace
Components, Circuits, Devices and Systems
Fields, Waves and Electromagnetics
Geoscience
Signal Processing and Analysis
Point cloud compression
Deep learning
Solid modeling
Three-dimensional displays
Laser radar
Atmospheric modeling
Vegetation
Airborne LiDAR
Tree species
Classification
3D
- Language
- ISSN
- 2153-7003
This paper applied a transformer based deep learning model 3D Point Cloud Transformer (3DPCT) to conduct a tree species classification of Airborne LiDAR data. There are a total 1291 single tree point clouds of 11 different species from coniferous and deciduous used in this paper. The model integrated the local and global feature learning modules from both pointwise and channel-wise, which provide promising results of tree species classification. We also investigate by adding more channels the classification results can be improved. Different number of points per each sample as the model input also deliver different accuracy. The highest overall accuracy of 11 categories classification achieved 86.1%, and precision and recall of each category provide more directions of future study.