BEEHIVE: A dataset of Apis mellifera images to empower honeybee monitoring research

• DOI: 10.1016/j.dib.2024.111055
• Publication Date: 2024-10-22T03:50:10Z
• Authors: Massimiliano Micheli; Giulia Papa; Ilaria Negri; Matteo Lancini; Cristina Nuzzi; Simone Pasinetti
• Keywords: Beehive; Research article

This data article describes the collection process of two sub-datasets comprehending images Apis mellifera captured inside a commercial beehive ("Frame" sub-dataset, 2057 images) and at bottom it ("Bottom" 1494 images). The was collected in spring 2023 (April-May) for "Frame" September "Bottom" sub-dataset. Acquisitions were carried out using an instrumented developed purpose monitoring colony's health status during long periods time. color cameras used equipped with different lenses accordingly (liquid internal one, standard lens 8 mm focal length) actuated by embedded board, alongside red LED strips to illuminate beehive. Images camera mostly out-of-focus, thus filtering procedure based on adoption focus measure operators keep only in-focus ones. All manually labelled experts 2-class bounding boxes annotations representing full visible bees (class "bee") blurred or occluded according sub-dataset ("blurred_bee" "occluded_bee" class). Annotations are provided YOLO v8 format. dataset can be useful entomology research empowered computer vision, especially counting tasks, behavior monitoring, pest management, since few occurrences Varroa destructor mites could present