WildDrone in action!

Drone image of ungulates in the Ol'Pejeta Conservancy, Kenya © 2025 G. May
First successful field deployment for drone-base wildlife conservation in Ol'Pejeta, Kenya.
Biodiversity is declining worldwide and we need urgently new ways to support conservation actions. The Marie Curie WildDrone network aims at developing technology fostering a new generation of drones for animal conservation, by connecting young researchers in biology, robotics and computer vision.
In the frame of ECEO’s involvement in the WildDrone research network, we completed our first field trip to Africa (Kenya) this January. Using advanced computer vision software developed in our lab, we are exploring the potential of drones for efficient and scalable monitoring of animal populations from the air.
To do so, we aim to train object detection models to identify animals of interest in the imagery recorded by the drones to automate an otherwise expensive and unsafe approach in which human observers spot wildlife from airplanes.
During this first field mission, we conducted some exploratory mapping of the Ol Pejeta Conservancy (Laikipia, Kenya), from which we obtained initial training data for our detection software. Our efforts will be continued and expanded in early 2026, when we will go back to Ol Pejeta to acquire more data.
WildDrone is an MSCA Doctoral Network funded by the European Union’s Horizon Europe research and innovation funding programme under the Marie Skłodowska-Curie grant agreement no. 101071224
G. May, B. Kellenberger, E. Dalsasso, and D. Tuia. POLO - Point-based, multi-class animal detection. In ECCV workshops, Computer Vision for Ecology, Milan, Italy, 2024 (arxiv paper).