WildBe dataset
Image dataset of wild berries collected in Ilomantsi (Finland) using drones flying under the canopy.
The WildBe data-set, contains approximately 3K images - extracted from more than 500 drone images - featuring 18K annotated bounding boxes. Images were taken from different drone models, encompassing variations of camera, albedo, forests, terrain, height, perspective changes, and displaying a grand total of 18468 berries. These include bilberry, cloudberry, crowberry and lingonberry, possibly at different ripening stages. Each image is timestamp-aligned with drone metadata.
WildBe Dataset is published with the paper
L. Riz, S. Povoli, A. Caraffa, D. Boscaini, M.L. Mekhalfi, P. Chippendale, ... , F. Poiesi. Wild Berry image dataset collected in Finnish forests and peatlands using drones. Under review [arXiv version]
Download and additional information
https://huggingface.co/datasets/FBK-TeV/WildBe (training, validation sets)
Copyright: The WildBe Dataset is published under the Creative Commons Attribution Non Commercial 4.0 License (CC BY NC 4.0). This means that you are required to attribute the work in the manner specified by the authors (e.g., citing the paper in the reference above). You are not allowed to use this work for commercial purposes. Additionally, if you choose to alter, transform, or build upon this dataset, you may distribute the resulting work under the same CC BY NC 4.0 license.
Aknowledgements
This work was carried out within the scope of the FEROX project that received funding from the European Union’s Horizon Framework Programme for Research and Innovation.