Inspecting the vineyard is an operation that takes place all year round. In BACCHUS we are developing a platform that will be able to carry out many inspection and data gathering tasks in the field, while assessing the crops.

The inspection platform

Based on the Thorvald platform, in BACCHUS we are building a mobile robot with effective and intelligent fusion of different sensor inputs and machine learning methods that will enable the “smart” capturing of information from the field. Some of the operations that this will carry out include:

  • the creation of accurate and representative spectral libraries that will ensure the development of machine learning methods using optimal input data,
  • the development of appropriate algorithms supporting the interpretation of different sensor inputs (e.g. plant health, grape ripeness, etc.) and their correlation to chemical measurements,
  • the deployment of data fusion techniques that will trigger active and/or on-demand learning as well as feed into adaptive algorithms for abnormal situations, forming a “curiosity-driven” agent.

The hyperspectral camera

A key component of the harvesting platform is the hyperspectral imaging capabilities. This camera will be able to assess the quality of the grapes, such as their sugar level, by simply looking at them. Looking at the spectral region ~450-950 nm, we can get the signature of the crops that will be used in BACCHUS with respect to their chemical composition.

Yield prediction

In BACCHUS will make dense predictions of harvest yield efficiently and automatically using cameras. An approach will be developed to automatically detect and count crops to forecast yield with both precision and accuracy. The approach is to take images from the robot camera through its navigation in the field in order to detect the crop and predict the yield.

Project Coordinator
Prof. Zoe Doulgeri
Automation & Robotics Lab
Aristotle University of Thessaloniki
Department of Electrical & Computer Engineering
Thessaloniki 54124, Greece

This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 871704.

The website reflects only the view of the author(s) and the Commission is not responsible for any use that may be made of the information it contains.

Bacchus Project BACCHUS Project
© 2020 - 2022 All rights reserved