Accurate segmentation of river water in close-range Remote Sensing (RS) images is vital for effective environmental monitoring. However, it's challenging due to water's dynamic nature and varying colors. While deep learning models have provided solutions, we explored Segment Anything | Meta AI for enhanced accuracy and efficiency in river water segmentation. We also introduced LuFI-RiverSnap dataset for water segmentation. Our findings are detailed in a fair comparison study:
A. Moghimi, M. Welzel, T. Celik and T. Schlurmann, "A Comparative Performance Analysis of Popular Deep Learning Models and Segment Anything Model (SAM) for River Water Segmentation in Close-Range Remote Sensing Imagery," in IEEE Access, doi: 10.1109/ACCESS.2024.3385425
This was the initial publication of the RiverSnap project, as part of "ZukunftslaborWasser" lead by Ludwig-Franzius-Institute for Hydraulic, Estuarine and Coastal Engineering and Leibniz Universität Hannover, supported by Zentrum für digitale Innovationen Niedersachsen funded by the Lower Saxon Ministry of Research and Culture
