A GS-based built-up area detection method using Polarimetric SAR images

Feature extraction and target detection using Polarimetric SAR image is of great interest in SAR applications. The current detection methods, such as Polarimetric Target Decomposition (PTD), Polarimetric Similarity Parameter (PSP) and Polarimetric Whitening Filter (PWF) can be used for target detection at different aspects. In order to combine their merits at the same time, a target detection method based on Granularity Synthesis (GS) theory is proposed in this paper, in which the detection results using PTD, PSP and PWF are combined using granularity synthesis algorithm based on quotient space theory and construct a fine and comprehensive detection result. The proposed target detection method is demonstrated with Danish EMISAR L-band full polarized image of the Foulum agricultural test site in Jutland, Denmark. The results confirmed that the proposed model is accurate and effective for detection and analysis of buildings in urban areas.