Detection of Lake Shoreline Based on Modified RSF Model Combined With Edge Energy and Global Energy for SAR Images

Lake shoreline detection plays an important role in hydrological structure analysis and urban ecology governance but is a challenging task in synthetic aperture radar (SAR) image interpretation. Due to the complex shoreline environment, the preservation of weak boundaries and fitting of global information in large-scale SAR images deserve further research. Thus, this letter proposes a novel coarse-to-fine lake shoreline detection approach for SAR images based on modified region-scalable fitting (RSF) model combined with edge energy and global energy. In this approach, SAR images are despeckled by the block-matching 3-D (BM3D) filter. Then a novel energy term based on Laplacian of Gaussian (LoG) operator and ratio of exponentially weighted averages (ROEWA) operator is constructed to accurately locate the boundary and reduce false boundary. Additionally, the global energy term is adopted to fit the global information well. The experimental results based on real data demonstrate that the proposed approach has a stronger ability to maintain weak edges compared with RSF model, which exhibits better effectiveness and reliability.