Research projects

BoniKI

AI-based scoring system for plant-accurate, autonomous plant evaluation

Start: 05/2021

End: 04/2024

The BoniKI project is concerned with the automation of plant evaluation. Plant evaluation – for example, the assessment of pest infestation in crops – is time-consuming, cost-intensive and requires many years of experience. Currently, a manual process is necessary, in which plants are randomly inspected and overall assessments are determined via statistical analyses.

Automated plant evaluation with artificial intelligence (AI) will increase sustainability, transparency, and efficiency in agriculture. The models and neural networks open up new potentials and relevant scoring parameters. They enable a larger circle of users to determine protection and maintenance measures.
The tasks and responsibilities of the FZI lie specifically in the field of AI. High-resolution data will be recorded with an Unmanned Aerial System (UAS) for a plant-specific evaluation and AI methods will be used to separate the crop plant from weeds and background before an automatic evaluation is carried out with further AI methods. At the end of the project, the goal is to create a holistic, easy-to-use solution that can automate and even self-learn the evaluation process.

Contact

personal-photo-georg-heppner

Georg Heppner

Department Manager
Division: Intelligent Systems and Production Engineering

Research Focus

Applied Artificial Intelligence

In this research focus, the FZI prioritizes the topics of Artificial Intelligence (AI) as well as human and AI engineering. In addition, the FZI deals with questions on dedicated AI hardware and predictive AI.

Funding notice:
The BoniKI project is funded by the Federal Office for Agriculture and Food.

Project partners:

More projects