This dataset includes drone (Uncrewed Aerial Vehicles, UAV) orthomosaics of three plots (each plot covers approx. 100 by 100 m) acquired in November 2017 in Waititu (Fjordland) New Zealand. The resolution (ground sampling distance) of the orthomosaics amounts to approx. 2-3 cm. The orthomosaics feature RGB information and an estimated canopy height (normalized digital surface model, nDSM). The canopy height was derived by subtracting digital surface models (DSM) with digital terrain models (DTM). The DTMs were estimated from the lowest points. Details are given in the publication below. The orthomosaics are partially labelled (polygon shapefiles) for the two tree species, which are Metrosideros umbellata, an angiosperm of the Myrtaceae and Dacrydium cupressinum, a gymnosperm of the Podocarpaceae. The two species are abbreviated as metumb and daccup, respectively. The covered forests are primary forests with a high species richness and endemism. Each orthomosaic comes with an AOI (area of interest, polygon shapefile) that indicates the areas where the labelling was performed. Within the extent of this AOI the two tree species are assumed to be completely delineated (by visual interpretation guided with insitu data; details see publication below). For visual inspection of the imagery we recommend to generate image pyramids since the image data has a very high spatial resolution. Details on the dataset are mentioned in the corresponding publication: Kattenborn, T., Eichel, J., Wiser, S., Burrows, L., Fassnacht, F. E., & Schmidtlein, S. (2020). Convolutional Neural Networks accurately predict cover fractions of plant species and communities in Unmanned Aerial Vehicle imagery. Remote Sensing in Ecology and Conservation, 6(4), 472-486. https://doi.org/10.1002/rse2.146 https://zslpublications.onlinelibrary.wiley.com/doi/full/10.1002/rse2.146 Acknowledgements: The data acquisition was funded by the Catalyst: Leaders program financed by the New Zealand Ministry of Business, Innovation and Employment (MBIE) and administered by the Royal Society of New Zealand and the MBIE Strategic Science Investment Fund to Manaaki Whenua-Landcare Research