Interdisciplinary Research Project on computer vision and intelligent mowing patterns

This project aims to deliver a unique, novel and first-ever approach to incorporate AI-technology in order to contribute to the biodiversity in our nature. More specifically, automated biologically optimised mowing strategies guided by computer vision and AI algorithms will be developed for the sustainable management of grasslands. The research performed in this project will aid the conservation of pollinator biodiversity in Flanders by restoring the bee habitat. Intensified land-use in agriculture, with monotonous crops and grasslands, is the main driver causing less floral resources and ultimately declining pollinator diversity. Adequate mowing strategies are needed in order to take current biodiversity characteristics of the grasslands into account.

This project brings together two research groups from very distinct disciplines, which become very complimentary in view of the envisaged research objectives:

  • Team Agrozoology from the Faculty of Bioscience Engineering will focus on extensive data collection and annotation for Arrhenius-type grasslands as well as co-designing the algorithm for automated mowing based on their extensive knowledge on sinus managed grasslands
  • Team IDLab-MEDIA from the Faculty of Engineering and Architecture will focus on capturing drone based RGB and hyperspectral footage and training computer vision and AI algorithms in order to recognise biodiverse regions in grasslands. Furthermore, IDLab-MEDIA will aid Agrozoology in the design of an automated mowing algorithm based on drone imagery

This project is funded by the Special Research Fund of Ghent University in the context of the bi-annual project call for Interdisciplinary Research Projects.