Estimating Individual Tree Height and Species from UAV Imagery

TL;DR

This paper introduces BIRCH-Trees, a new benchmark dataset, and DINOvTree, a unified vision model for estimating individual tree height and species from UAV imagery, demonstrating high accuracy and efficiency across diverse forest types.

Contribution

The paper presents the first benchmark for tree height and species estimation from UAV images and a novel unified model that outperforms existing methods in accuracy and parameter efficiency.

Findings

DINOvTree achieves top overall results in height and species estimation.

DINOvTree uses only 54-58% of the parameters compared to the second-best approach.

The approach is effective across temperate, tropical, and boreal forest datasets.

Abstract

Accurate estimation of forest biomass, a major carbon sink, relies heavily on tree-level traits such as height and species. Unoccupied Aerial Vehicles (UAVs) capturing high-resolution imagery from a single RGB camera offer a cost-effective and scalable approach for mapping and measuring individual trees. We introduce BIRCH-Trees, the first benchmark for individual tree height and species estimation from tree-centered UAV images, spanning three datasets: temperate forests, tropical forests, and boreal plantations. We also present DINOvTree, a unified approach using a Vision Foundation Model (VFM) backbone with task-specific heads for simultaneous height and species prediction. Through extensive evaluations on BIRCH-Trees, we compare DINOvTree against commonly used vision methods, including VFMs, as well as biological allometric equations. We find that DINOvTree achieves top overall results with accurate height predictions and competitive classification accuracy while using only 54% to 58% of the parameters of the second-best approach.