"BonnBeetClouds3D: A Dataset Towards Point Cloud-Based Organ-Level Phenotyping of Sugar Beet Plants Under Real Field Conditions"
The main contribution of this paper is a large dataset covering 48 different varieties of sugar beets that we recorded on real breeding trials with over 3,000 plants, with pointwise annotations for individual plants and leaves enabling the development and evaluation of segmentation, detection and actual in-field phenotyping algorithms. To allow for direct evaluation of tasks such as extraction of phenotypic traits, we also provide reference values for commonly evaluated traits.
Paper:
E. A. Marks, J. Bömer, F. Magistri, A. Sah, J. Behley, and C. Stachniss, “BonnBeetClouds3D: A Dataset Towards Point Cloud-Based Organ-Level Phenotyping of Sugar Beet Plants Under Real Field Conditions,” in Proc. of the IEEE/RSJ Intl. Conf. on Intelligent Robots and Systems (IROS), 2024.
https://www.ipb.uni-bonn.de/wp-content/papercite-data/pdf/marks2024iros.pdf
"Spatio-Temporal Consistent Mapping of Growing Plants for Agricultural Robots in the Wild"
Tracking the change of growing plants is important for automating phenotyping and robots managing crops. This paper proposes a new system that uses a 3D model of plants along crop rows to enable sensor localize even in the presence of heavy changes and deforming the plant model to adapt it to the new measurements. The work obtains accurate 4D models of the plants and track the plant traits’ evolution over time.
Paper:
L. Lobefaro, M. V. R. Malladi, T. Guadagnino, and C. Stachniss, “Spatio-Temporal Consistent Mapping of Growing Plants for Agricultural Robots in the Wild,” in Proc. of the IEEE/RSJ Intl. Conf. on Intelligent Robots and Systems (IROS), 2024.
https://www.ipb.uni-bonn.de/wp-content/papercite-data/pdf/lobefaro2024iros.pdf
https://youtu.be/bnWZWd5DHTg