(2024-2028, ref. ANR-24-CE23-1586).It is now possible to digitize the shape of a plant during its growth in three dimensions (3D) using photogrammetry or remote sensing. Resulting time-varying 3D point clouds contain rich information about plant growth and have the potential to significantly impact phenotyping applications, from research to agriculture. However, tools to automatically process and analyse this data robustly are still missing. The overall goal of the 4DPlants project is to invent solutions that will make plant phenotyping in 3D and over time more reliable and accessible to plant scientists. Its key idea is to learn a sparse and semantic latent representation of growing plants using L-systems, a state-of-the-art tool in plant modelling.
The 4DPlants project has received funding from the (2024-2028, ref. ANR-24-CE23-1586).