Our research in remote sensing involves using deep learning methods to analyze satellite and aerial imagery. We are interested in both methodological and applied aspects of the research.
Crop identification using Time Series Analysis
We are using time series analysis on satelite multi-spectral data (Sentinel-2) to identify different crops in Slovenia. Our focus is on early identification of crops in relation to temporal and spatial transferability of the models.
Publications
Terraced landscapes
We are using deep learning for semantic segmentation to analyze LIDAR data of Slovenian lanscape and identify terraced landscapes. Methodological challenges include noisy labels and unbalanced classes. We are also interested in transferability of the models to other regions.