Subject	Computer Science and Pattern Recognition
Specific subject area	Remote Sensing, Machine vision, Deep learning, Image classification, Flower detection, Precision agriculture, Yield estimation
Data format	Raw
Type of data	Table, Image, Text
Data collection	The data are divided into three sets according to the collection years, 2018, 2019 and 2020. Different flying altitudes were conducted for each year. All the three field campaigns were taken during the full blooming period, in late April. The weather condition of data 2018 is overcast, and the other two years are sunny, which benefits the algorithm robustness development. Flying missions were set to autonomous mode, and images collected were geotagged.
Data source location	Institution: Field Crops, Wageningen University & Research City/Town/Region: Randwijk, Overbetuwe Country: the Netherlands GPS coordinates for collected data: WGS84 / UTM zone 31N (EPSG::32631)
Data accessibility	Repository name: Zenodo Data identification number: https://doi.org/10.5281/zenodo.6802308 Direct URL to data: https://zenodo.org/record/6802308#.YvvMFuxBz0p Instructions for accessing these data: All the data are compressed into a .zip file which can be downloaded directly via the link shared above. The data are available after decompressing.
Related research article	C. Zhang, J. Valente, W. Wang, L. Guo, A. Tubau Comas, P. van Dalfsen, B. Rijk, L. Kooistra, Feasibility assessment of tree-level flower intensity quantification from UAV RGB imagery: A triennial study in an apple orchard, ISPRS Journal of Photogrammetry and Remote Sensing 197 (2023) 256-273. https://doi.org/10.1016/j.isprsjprs.2023.02.003