Fusion of intensity/coherent information using region covariance features for unsupervised classification of SAR imagery

Abstract

Unsupervised classification of synthetic aperture radar (SAR) imagery is an essential step in SAR image interpretation. There is a growing demand for an efficient way to fuse multi-information of SAR imagery. This paper presents an intensity/coherent information fusion algorithm by using region covariance features for unsupervised classification. More precisely, we firstly extract the intensity properties and coherent characteristics from each pixel of SAR imagery, then use the region covariance descriptor to fuse the intensity and coherent features, and finally exploit the K-means algorithm to obtain the final unsupervised classification map. Experimental results on SAR imagery demonstrate the effectiveness of the proposed fusion scheme.