Data were collected in 2019 in Dikopshof, Wesseling, Germany

This data set is generated by the bio-economic farm-level model FarmDyn (https://farmdyn.github.io/documentation/). X_raw.parquet.gzip contains the input data (77 variables), and Y_raw.parquet.gzip contains the corresponding output data (248 output variables). A farm in FarmDyn maximizes its profit based on the what input values are given (e.g. crop prices, farm size, etc.). The output variables are either a farm's decisions of farming activites or the outcomes of its decisions. The data can be read in python by pd.read_parquet.

The corn Dataset (CN20) was captured using BonnBot-I. This is a challenging dataset for crop monitoring approaches as it is a grass crop.

µCt images with a resolution of 11µm

Shape completion dataset for sweet peppers. A detailed description of the dataset can be found in our technical report: https://www.ipb.uni-bonn.de/wp-content/papercite-data/pdf/magistri2024arxiv.pdf We additionally provide a small set of python script to load this data: https://github.com/PRBonn/shape_completion_toolkit

The effect of a mucilage analogue from chia seeds without intrinsic respiratory activity on oxygen diffusion was measured at different water contents during wetting-drying cycles in a diffusion chamber experiment. Artificial soils of various particle size distributions were mixed with various amounts of the mucilage analogue. Additionally, environmental scanning electron microscopy (ESEM) was used to visualize mucilage bridges in the dry soil samples.

A sweet pepper dataset which was captured in the CKA glasshouse using PathoBot. It contains differently coloured sweet peppers in various ripening stages. More information, citations and a related previous dataset can be found at http://agrobotics.uni-bonn.de/sweet_pepper_dataset/

SB20 is a sugar beet dataset that was captured at a field on campus Klein Altendorf of the University of Bonn. The data was captured by mounting an Intel RealSense D435i sensor with a nadir view of the ground on a Sagarobot. It contains RGB-Dimages of sugarbeet and eight different categories of weeds covering a range of growth stages, natural world illumination conditions, and challenging occlusions. The dataset provides multi-class annotations.

The dataset contains 7 maize plants measured on 12 days. This gives 84 maize point clouds (about 90 Mio. points). From these, 49 point clouds (about 60 Mio. points) are labeled. Furthermore, the dataset contains 7 tomato plants measured on 20 days (about 350 Mio. points). This gives 140 point clouds from which 77 point clouds (200 Mio. points) are labeled. Note that we provide temporally consistent labels for each point in the clouds. We provide labeled and unlabeled point clouds, the file name indicates whether the point cloud is annotated or not. For example, M01_0313_a.xyz is labeled, M01_0314.xyz is not labeled. For the tomato plant point clouds, each annotated file contains the x,y,z coordinates, and the label associated with the point. For the maize point clouds. Each file annotated contains the x,y,z coordinates, and the 2 labels associated with the point. For both species, if no labels are provided, the files contain only the x,y,z coordinates. Cite: D. Schunck, F. Magistri, R. A. Rosu, A. Cornelißen, N. Chebrolu, S. Paulus, J. Léon, S. Behnke, C. Stachniss, H. Kuhlmann, and L. Klingbeil, “Pheno4D: A spatio-temporal dataset of maize and tomato plant point clouds for phenotyping and advanced plant analysis,” PLOS ONE, vol. 16, iss. 8, pp. 1-18, 2021. doi:10.1371/journal.pone.0256340.