GYMNSA dataset

Annotated image dataset with different stages of European pear rust in orchards for UAV-based automatic symptom detection.

The evaluation of fruit genetic resources regarding a resistance to pathogens is an essential basis for subsequent selection in fruit breeding. Both genetic analysis and phenotyping of defined traits are important tools and provide decision data in the evaluation process. However, the phenotyping of plants is often carried out "by hand" and remains the bottleneck in fruit breeding and fruit growing. The development of a digital and UAV (unmanned aerial vehicle)-based phenotyping method for the assessment of genotype-specific susceptibility or resistance against diseases in orchards would significantly increase the efficiency of plant breeding. In this framework, a workflow for drone-based monitoring of pathogens in orchards was developed using the European pear rust (Gymnosporangium sabinae) as model pathogen. We provide a dataset with expert-annotated high-resolution RGB images with pear rust symptoms. The UAV images present different pear genotypes, including varieties, wild species and progeny from breeding. The dataset contains manually labelled images with a size of 768 x 768 pixels of leaves infected with pear rust at different stages of development, labelled as class GYMNSA, as well as background images without symptoms. A total of 584 annotated images and 162 background images, organized into a training and validation set, are included in the GYMNSA dataset. This dataset can be used as a resource for researchers and developers working on drone-based plant disease monitoring systems.