Unsupervised segmentation of synthetic aperture radar inundation imagery using the level set method

In this paper, we proposed an unsupervised algorithm to identify the flooded areas from synthetic aperture radar (SAR) images based on texture information derived from the gray-level co-occurrence matrices (GLCM) texture analysis. Here, five GLCM features, namely, energy, contrast, homogeneity, correlation and entropy, are extracted from a SAR image. These features are input to an image segmentation algorithm using a level set method to identify flooded and dry areas. Experiments were conducted on the RADARSAT-2 images of severely flooded areas near Chaopraya rivers, Thailand, in 2011, for which contemporaneous ground data exists for validation. Our results demonstrate that the proposed algorithm is able to successfully segment various flood regions and achieve improvement over existing published unsupervised algorithms.