An edge attention-based geodesic distance for PolSAR image superpixel segmentation

The simple linear iterative clustering (SLIC) is the most popular superpixel segmentation method for its simplicity and effectiveness. In this Letter, we propose an edge attention-based geodesic distance, which can be applied to the SLIC framework for polarimetric synthetic aperture radar image superpixel segmentation. Image edges are especially considered to generate superpixels with better boundary adherence property, while the computing burden does not increase. Specifically, the authors first detect image edges, then fuse the edge map and polarimetric dissimilarity, and finally define the geodesic distance based on the fused results. Experiments performed on real scene images demonstrate the superiority of the proposed distance in both qualitative and quantitative ways.