Toward Consistent Canopy Characterization From Low-Cost UAV Imagery
Monitoring tropical forest structure at landscape scale requires cost-effective methods capable of bridging the gap between field inventories and satellite remote sensing products. However, the diversity of available individual tree crown (ITC) segmentation algorithms raises questions about the consistency and reliability of derived structural metrics. We evaluated three ITC segmentation algorithms — Detectree2, SAM, and the hybrid Detectree2SAM (D2S) — applied to very high-resolution RGB orthomosaics (5cm resolution) acquired over ~200ha of the Luki Biosphere Reserve (Democratic Republic of Congo) using a low-cost drone. Algorithms were validated at the individual scale against a photointerpretation reference of 1882 manually delineated crowns and at the plot scale against a field inventory of 360 trees across 18 plots. At the individual scale, IoU-based F1 scores ranged from 0.57 (D2S) to 0.67 (SAM). At the plot scale, D2S provided the most accurate crown area estimates (RMSD=26%-29%), while SAM best reproduced canopy density (RMSD=22%). A linear bias correction substantially reduced prediction errors and improved cross-algorithm convergence, yielding consistent estimates of crown area and canopy density. The authors propose a three-step operational pipeline — plot-scale field validation, per-algorithm linear bias correction, and landscape-scale aggregation — that delivers consistent, ecologically interpretable structural estimates from low-cost UAV imagery.