A brief introduction through the university’s eyes – Rasmus N. Jørgensen and Michael Nørbo
What happens when plant protection specialists, insect experts, software developers and agricultural researchers work together to make farming more precise?
Follow along with this video where Rasmus N. Jørgensen gives you a walkthrough of the developments in the OdinsAEye project and how we handle and process the data behind the scenes with the help of Jupiter, a user interface developed by the amazing Michael Nørbo. This video also highlights the collaboration and exchange of data and knowledge between industry and academia, so that our results can be used not only in the theory but also in practice.
This is exactly the focus of the OdinsAEye project.
In the video you can see how the project brings together expertise from plant protection, insect identification, software development, ECE and Agroecology, supported by collaboration with RoboWeedMaps, Patriotisk Selskab and I·GIS. Together, the partners are working to transform field images into useful information for farmers and agricultural consultants.
See how we go from field images to intelligent data
Images are collected under real field conditions and different weather conditions using several technologies, including ATV-mounted cameras and CropCareCam.
These images are processed using advanced models that can map weeds, analyse crop populations and monitor crop development. The project is also expanding into mature crop analysis and insect detection, including dry matter estimation and identification of specific insect groups.
A dedicated server environment at I·GIS supports secure processing and analysis of the collected data.
Experience how we make data useful
Collecting images is only the first step. The real value comes from turning them into information that can support decisions.
OdinsAEye provides tools for exploring species distributions, field maps and the development of individual objects over time. For farmers and consultants, this can mean identifying specific weed problems in particular fields and using that information to support more targeted treatments.
And remember: it is a continuous learning process
The project follows a continuous feedback loop:
Collect → Analyse → Quality-check → Improve → Collect again
New field data helps improve the models, while quality control and expert knowledge ensure that the results remain relevant to real agricultural conditions.
Supported by Innovation Fund Denmark, with additional contributions from Novo, OdinsAEye is exploring how AI, imaging and agricultural expertise can work together to create better digital tools for precision agriculture.
From images to data. From data to knowledge. From knowledge to better decisions in the field.