Bayesian Machine Learning with Uncertainty Quantification for Detecting Weeds in Crop Lands from Low Altitude Remote Sensing | AI4Weed
This PhD project is a part of the HEIBRiDS (Helmholtz Einstein International Berlin Research School in Data Science) PhD Program. The main objective is weed identification and monitoring in agricultural fields using low-altitude remote sensing imagery. To this end, UAV (ie. drones) data is used in combination with Bayesian machine learning techniques, which enable uncertainty quantification and more reliable estimates.
- Helmholtz-Einstein International Berlin Research School in Data Science
- Einstein Center Digital Future (ECDF)
- Celikkan, Ekin, Mohammadmehdi, Saberioon, Martin, Herold, Nadja, Klein. "Semantic Segmentation of Crops and Weeds with Probabilistic Modeling and Uncertainty Quantification." Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops. 2023.
- Celikkan, Ekin, Timo, Kunzmann, Yertay, Yeskaliyev, Sibylle, Itzerott, Nadja, Klein, Martin, Herold. "WeedsGalore: A Multispectral and Multitemporal UAV-Based Dataset for Crop and Weed Segmentation in Agricultural Maize Fields." Proceedings of the Winter Conference on Applications of Computer Vision (WACV). 2025.
