PCTreeS: 3D Point Cloud Tree Species Classification Using Airborne LiDAR Images

TL;DR

This paper introduces PCTreeS, a novel deep learning approach using 3D point cloud images and vision transformers for scalable and accurate tree species classification from airborne LiDAR data, outperforming CNN-based methods.

Contribution

It applies a vision transformer directly to 3D LiDAR point cloud images for tree classification, demonstrating improved accuracy and efficiency over traditional CNN approaches.

Findings

PCTreeS achieves higher AUC and accuracy than CNN baselines.

The approach reduces training time to approximately 45 minutes.

It successfully classifies tree species in tropical savannas using airborne LiDAR.

Abstract

Reliable large-scale data on the state of forests is crucial for monitoring ecosystem health, carbon stock, and the impact of climate change. Current knowledge of tree species distribution relies heavily on manual data collection in the field, which often takes years to complete, resulting in limited datasets that cover only a small subset of the world's forests. Recent works show that state-of-the-art deep learning models using Light Detection and Ranging (LiDAR) images enable accurate and scalable classification of tree species in various ecosystems. While LiDAR images contain rich 3D information, most previous works flatten the 3D images into 2D projections to use Convolutional Neural Networks (CNNs). This paper offers three significant contributions: (1) we apply the deep learning framework for tree classification in tropical savannas; (2) we use Airborne LiDAR images, which have a lower resolution but greater scalability than Terrestrial LiDAR images used in most previous works; (3) we introduce the approach of directly feeding 3D point cloud images into a vision transformer model (PCTreeS). Our results show that the PCTreeS approach outperforms current CNN baselines with 2D projections in AUC (0.81), overall accuracy (0.72), and training time (~45 mins). This paper also motivates further LiDAR image collection and validation for accurate large-scale automatic classification of tree species.