EWIS2 (2023-2026)
funded by Bavarian State Ministry for Food, Agriculture, Forests and Tourism
We are conducting research in several funded projects. You can find more information about EWIS2 below. If you are interested in more details and discussions about our projects, do not hesitate to contact us.
For more information please contact Dominik Grimm.
Project Description
Sorghum and Maize are important energy crops in Bavaria, but their yield is often diminished by the growth of unwanted weeds. Precision Farming offers an unprecedented opportunity to automate and optimize processes in agriculture to manage weeds on agricultural fields more precisely based on their needs and lower the amount of pesticides. This could also minimize the risk of erosion of fields that are located on hills.
In this project we aim to generate high-precision weed density maps with the help of drone images and artificial intelligence. Moreover, based on this weed mapping, a profitability assessment is carried out for various options of site-specific weed management measures. Finally, these weed density maps will be integrated in different agricultural robots to perform mechanical weed management.
This image was created with the assistance of DALL·E 3
Project Information:
Project title: Development and evaluation of weed application maps for the use of robots in mechanical weed control applications
Involved people in our team:
- Project Coordinator: Prof. Dr. Dominik Grimm
- Project Advisor: Nikita Genze
Funding: Bayerisches Staatsministerium für Ernährung, Landwirtschaft, Forsten und Tourismus
Project partner: Michael Grieb, Maria Vilsmeier, Technologie- und Förderzentrum TFZ; Johanna Pfeiffer, Stefan Kopfinger, Markus Gandorfer, Bayerische Landesanstalt für Landwirtschaft (LfL), ILT 6, Arbeitsbereich Digitalisierung
Funding ID: G2/N/22/11
Publications
Improved weed segmentation in UAV imagery of sorghum fields with a combined deblurring segmentation model.
N Genze, M Wirth, C Schreiner, R Ajekwe, M Grieb, DG Grimm
Plant Methods, Vol. 19, 87, 2023
(https://doi.org/10.1186/s13007-023-01060-8) [Code] [Data]
