PFruitlet640 (PearFruitlet640)

Dataset contains annotated photographs of pear fruitlets for object detection tasks using YOLO architecture. It has only one class "Pear fruitlet". The digital images of pear fruitlets were collected in the experimental site of the Institute of Horticulture (LatHort) with cultivars ‘Suvenirs’, ‘Vasarine Sviestine’ and ‘Mramornaya’ on seedling rootstocks ‘Kazraushu’ with planting distances 4×5 m (500 trees per 1 ha). (Krimūnu parish, Dobeles district, Latvia: 56.610169, 23.305956). The collection of fruitlet images of ‘Suvenirs’, ‘Vasarine Sviestine’ and ‘Mramornaya’ was done at the beginning of August (79 days after full bloom). The collection of digital images was carried out using a photo camera of mobile device Huawei P 40: 50 MP Ultra Vision Camera (Wide Angle, f/1.9 aperture) + 16 MP Ultra-Wide Angle Camera (f/2.2 aperture) + 8 MP Telephoto Camera (f/2.4 aperture, OIS), the image size: 3000×4000 px; 5.0 MP. The collection of images was carried out in field conditions in 2022, in the orchard at the distance from the tree planting point 2.5 m (middle of alleyway). The whole canopy of trees was photographed as separate objects. The images were taken in the front of a tree (a tree trunk, a planting point), perpendicularly the tree row from the west side of rows (the rows of pear trees oriented from north to south) before noon (10:00–12:00) at natural light conditions. The dataset was annotated for YOLO architecture by team of Rezekne Academy of Technologies.

Source: https://www.kaggle.com/datasets/projectlzp201910094/pfruitlet640

Presented in S. Kodors, M. Sondors, I. Apeinans, I. Zarembo, G. Lacis, E. Rubauskis and K. Karklina. "Importance of mosaic augmentation for agricultural image dataset", Agronomy Research, 2024.

License CC BY 4.0