Forest Tree Detection and Segmentation using High Resolution Airborne LiDAR

TL;DR

This paper introduces a deep learning-based method for autonomous tree detection and segmentation in high-resolution airborne LiDAR data, demonstrating improved performance through transfer learning across different sites.

Contribution

It presents a novel application of region-based CNN and 3D-CNN algorithms for tree segmentation, including a transfer learning strategy for limited training data scenarios.

Findings

The approach outperforms existing methods in tree detection accuracy.

Transfer learning enhances segmentation performance with limited site-specific data.

Validated on two commercial pine plantations with favorable results.

Abstract

This paper presents an autonomous approach to tree detection and segmentation in high resolution airborne LiDAR that utilises state-of-the-art region-based CNN and 3D-CNN deep learning algorithms. If the number of training examples for a site is low, it is shown to be beneficial to transfer a segmentation network learnt from a different site with more training data and fine-tune it. The algorithm was validated using airborne laser scanning over two different commercial pine plantations. The results show that the proposed approach performs favourably in comparison to other methods for tree detection and segmentation.