Estimating Individual Tree Height and Species from UAV Imagery

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.

Figures (23)

• Figure 1: Overview of our benchmark BIRCH-Trees and method DINOvTree. BIRCH-Trees is a benchmark for joint individual tree height estimation and species identification from images. DINOvTree includes a backbone with two task-specific heads.
• Figure 2: Examples from the BIRCH-Trees benchmark. It consists of tree-centered RGB images from three forest types with height and class label.
• Figure 3: Segmentation boundary buffering. The pixel bounded by the pink and purple contours correspond to the original segmentation $S$ and the buffered one $S_\text{buf}$.
• Figure 4: Class histograms of the Quebec Trees, BCI and Quebec Plantation datasets. Distributions per split are in App. \ref{['app:class_distribution']}.
• Figure 5: Height histograms of the Quebec Trees, BCI and Quebec Plantation datasets with 1m intervals. Distributions per split are in App. \ref{['app:height_stats']}.