A high-resolution UAV RGB imagery dataset for semantic segmentation of ground covers in urban community gardens — 24 orthomosaics across five gardens in Munich (2021–2022), manually annotated into eight ground-cover classes, with Train/Val/Test splits and a patch-based version for deep learning.
![[Data & Code] A drone imagery dataset for semantic segmentation of urban garden ground covers in biodiversity studies](/data/uav-rgb-orthomosaics-urban-garden-biodiversity/Fig6_GroundCovermasks_hu_4852e28b35fd9d93.webp)