Scattering Feature-Driven Superpixel Segmentation for Polarimetric SAR Images

Abstract

Superpixel segmentation for polarimetric synthetic aperture radar (PolSAR) images plays a fundamental role in various PolSAR applications. Subject to the intrinsic limitations, the existing methods generally produce over or undersegmented superpixels in highly complex scenes of PolSAR images. In this article, we propose an efficient and effective scattering feature-driven superpixel segmentation method for PolSAR images, which is capable of preserving the global structure information and producing superpixels with both high boundary adherence and visual compactness. First, a hierarchical version of the refined five-component decomposition is proposed. The derived scattering features along with other well-used features are then combined to construct a low-dimensional feature vector. Second, a modified normalized cuts formulation using a distance measurement is presented, in which the feature similarity and the space proximity are both considered. During the superpixel segmentation, the edge information derived from our scattering mechanism-optimal contrast-based edge detector is incorporated. On this basis, a tradeoff factor according to the edge information and the equivalent number of looks is determined, which balances the relationship of feature similarity and space proximity so as to adaptively control the size and shape of superpixels. The performance of the proposed method is demonstrated and evaluated with fully PolSAR data over different test sites. The outputs show that the proposed method outperforms the state-of-the-art methods and the produced superpixels scale well especially for heterogeneous scattering cases.