wGrapeUNIPD-DL: an open dataset for white grape bunch detection
National and international Vitis variety catalogues can be used as image datasets for computer vision in viticulture. These databases archive ampelographic features and phenology of several grape varieties and plant structures images (e.g. leaf, bunch, shoots). Although these archives represent a potential database for computer vision in viticulture, plant structure images are acquired singularly and mostly not directly in the vineyard. Localization computer vision models would take advantage of multiple objects in the same image, allowing more efficient training. The present images and labels dataset was designed to overcome such limitations and provide suitable images for multiple cluster identification in white grape varieties. A group of 373 images were acquired from later view in vertical shoot position vineyards in six different Italian locations at different phenological stages. Images were then labelled in YOLO labelling format. The dataset was made available both in terms of images and labels. The real number of bunches counted in the field, and the number of bunches visible in the image (not covered by other vine structures) was recorded for a group of images in this dataset.
The database is divided into three levels. The primary dataset folder contains two sub-folders, named Calibrated_Images (271 images) and Uncalibrated_Images (102 images), respectively. These two folders represent the first level. The Calibrated_Imgaes folder contains two sub-folders (which represent the second level), named with_Counting (24 images) and without_Counting (247 images). Uncalibrated_imgaes folder, at the second level, contains only one sub-folder, named without_Bunches, where all images are included. The with_Counting folder comprises a text file (_counting.txt) with the real number of bunches counted in the field and the number of bunches visible in the image (not covered by other vine structures). The third level is represented by folders contained in the second level sub-folder, which names correspond to the varieties, the phenology and the acquisition date of the included images (e.g. Chardonnay_BBCH75_20_06_20). All images contained in each folder are matched with the associated label, which has the same name.