Object-Based Classification of PolSAR Images Based on Spatial and Semantic Features

High-resolution polarimatric synthetic aperture radar (PolSAR) images can provide more detail information on land-cover types and increase the image complexity at the same time. Traditionally, pixel-based image classification that takes image pixel as a processing unit cannot make full use of various features contained in high-resolution remote sensing images, and thus may not obtain satisfactory results. Hence, object-based image classification (OBIC) methods using image objects as processing units have been introduced into the PolSAR image classification. However, current researches on OBIC methods for PolSAR images usually could not take advantage of multiscale information of image objects, leading to some results that are not as satisfactory as expected. In this article, a multilevel image description consisting of proposed pixel-level spatial and object-level semantic features is developed for OBIC of PolSAR images. At the image pixel level, based on th combination of polarimetric and morphological image descriptions, polarimetric morphological profiles are developed to describe pixel-level spatial features. At the image object level, based on the construction of object adjacent graph, an object-level semantic indicator is proposed, which takes into account the contextual neighborhood of image objects. Finally, the proposed pixel-level spatial and object-level semantic features are integrated and incorporated in an OBIC scheme for the PolSAR image classification. Two fully polarized datasets acquired by ESAR and uninhabited airborne vehicle synthetic aperture radar (UAVSAR), respectively, are adopted to evaluate the effectiveness of the proposed method. The experimental results validate that the comprehensive utilization of both pixel-level and object-level features can effectively improve the OBIC accuracy of PolSAR images.