The GrassClover Image Dataset for Semantic and Hierarchical Species Understanding in Agriculture

GrassClover is a diverse image and biomass dataset collected in an outdoor agricultural setting. The images contain dense populations of grass and clover mixtures with heavy occlusions and occurrences of weeds. Fertilization and treatment of mixed crops depend on the local species composition. Therefore, the overall challenge is related to predicting the species composition in the canopy image and in the biomass. The dataset is collected with three different acquisition systems with ground sampling distances of 4-8 px/mm. The observed mixed crops vary both in setting (field vs plot trial), seed compositions, yield, years since establishment and time of the season. Synthetic training images with pixel-wise hierarchical and instance labels are provided for supervised training. 31 600 unlabeled images are additionally provided for pre-training, semi-supervised training or unsupervised training. Furthermore, this paper provides challenges of semantic segmentation and prediction of the biomass compositions and a baseline model for this dataset.