SAR Image Classification Based on CRFs With Integration of Local Label Context and Pairwise Label Compatibility

Abstract

Context information plays a critical role in SAR image classification, as high-resolution SAR data provides more information on scene context and visual structures. This paper presents a novel classification method for SAR images based on conditional random fields (CRFs) with integration of low-level features, local label context, and pairwise label compatibility. First, we extract the low-level features used in the SVM-based unary classifier for SAR images. The supertexture is newly introduced as one of the low-level features to model the texture context between image patches. Then, we describe the context information, including local context potential and pairwise potential. Incorporation of the category context helps to resolve the ambiguities of the unary classifier. The performance of our approach in both accuracy and visual appearance for high-resolution SAR image classification is proved in the experiments.