Positioning radiata pine branches requiring pruning by drone stereo vision

TL;DR

This paper develops a drone-mounted stereo vision system to detect and localize radiata pine branches for autonomous pruning, comparing various segmentation and depth estimation methods.

Contribution

It introduces a pipeline combining deep learning-based segmentation with multiple depth estimation techniques and a centroid triangulation algorithm for forestry applications.

Findings

Deep learning disparity maps are more coherent than traditional methods at 1-2 m distances.

The proposed system demonstrates feasibility of low-cost stereo vision for automated forestry tasks.

Abstract

This paper presents a stereo-vision-based system mounted on a drone for detecting and localising radiata pine branches to support autonomous pruning. The proposed pipeline comprises two stages: branch segmentation and depth estimation. For segmentation, YOLOv8, YOLOv9, and Mask R-CNN variants are compared on a custom dataset of 71 stereo image pairs captured with a ZED Mini camera. For depth estimation, both a traditional method (SGBM with WLS filtering) and deep-learning-based methods (PSMNet, ACVNet, GWCNet, MobileStereoNet, RAFT-Stereo, and NeRF-Supervised Deep Stereo) are evaluated. A centroid-based triangulation algorithm with MAD outlier rejection is proposed to compute branch distance from the segmentation mask and disparity map. Qualitative evaluation at distances of 1-2 m indicates that the deep learning-based disparity maps produce more coherent depth estimates than SGBM, demonstrating the feasibility of low-cost stereo vision for automated branch positioning in forestry.