SegmentAnyTree: A sensor and platform agnostic deep learning model for tree segmentation using laser scanning data

This study focuses on advancing individual tree crown (ITC) segmentation in lidar data, developing a sensor-and platform-agnostic deep learning model transferable across a spectrum of airborne (ULS), terrestrial (TLS), and mobile (MLS) laser scanning data. In a field where transferability across different data characteristics has been a longstanding challenge, this research marks a step towards versatile, efficient, and comprehensive 3D forest scene analysis. Central to this study is model performance evaluation based on platform type (ULS vs. MLS) and data density. This involved five distinct scenarios, each integrating different combinations of input training data, including ULS, MLS, and their sparsified versions, to assess the model's adaptability to varying resolutions and efficacy across different canopy layers. The core of the model, inspired by the PointGroup architecture, is a 3D convolutional neural network (CNN) with dedicated prediction heads for semantic and instance segmentation. The model underwent comprehensive validation on publicly available, machine learning-ready point cloud datasets. Additional analyses assessed model adaptability to different resolutions and performance across canopy layers. Our results reveal that point cloud sparsification as an augmentation strategy significantly improves model performance. It extends the model's capabilities to sparse LiDAR data and boosts detection and segmentation quality in dense, complex forest environments.