Unsupervised classification based on non‐negative eigenvalue decomposition and Wishart classifier. Issue 8 (1st October 2014)

• Record Type: Journal Article
• Authors: Wang, Chunle; Yu, Weidong; Wang, Robert; Deng, Yunkai; Zhao, Fengjun; Lu, Youchun
• Is Part Of: IET radar, sonar & navigation. Volume 8:Issue 8(2014)
• Page Start: 957
• Page End: 964
• Publication Date: 2014-10-01
• Subjects: radar polarimetry -- image classification -- eigenvalues and eigenfunctions -- synthetic aperture radar -- land use -- remote sensing by radar -- geophysical image processing -- surface scattering -- terrain mapping; unsupervised terrain classification -- nonnegative eigenvalue decomposition -- Wishart classifier -- land‐use classification algorithm -- polarimetric synthetic aperture radar image analysis -- nonreflection symmetry condition -- NNED -- Arii volume scattering model -- double bounce scatterings -- scattering characteristic parameter -- dominant scattering component -- German Aerospace Center E‐SAR polarimetric data -- Oberpfaffenhofen area -- Germany -- volume scattering model -- surface scattering model; Signal processing -- Periodicals; Radar -- Periodicals; Sonar -- Periodicals; Electronics in navigation -- Periodicals; Navigation -- Periodicals; 621.3848
• DOI: 10.1049/iet-rsn.2014.0076
• Languages: English
• ISSNs: 1751-8784

Abstract

Abstract : In this study, the authors propose an unsupervised terrain and land‐use classification algorithm for polarimetric synthetic aperture radar (SAR) image analysis. Under the non‐reflection symmetry condition, the non‐negative eigenvalue decomposition (NNED) employing Arii volume scattering model is derived. They first apply NNED to divide pixels into three categories of surface, volume and double bounce scatterings. Then the pixels in each category are further divided into several classes based on the scattering characteristic parameter of the dominant scattering component. Utilising the initial classification result as training sets, the complex Wishart classifier can then be performed within each category or beyond categories to refine the final classification result. The effectiveness of this algorithm is demonstrated using the German Aerospace Center's E‐SAR polarimetric data acquired over the Oberpfaffenhofen area in Germany.