Airborne SAR and optical image fusion based on IHS transform and joint non-negative sparse representation

Abstract

In this paper, a novel airborne synthetic aperture radar (SAR) and optical image fusion method based on Intensity-Hue-Saturation (IHS) and joint non-negative sparse representation (JNNSR) is proposed. Firstly, the color optical image is transformed into IHS space. Then, the intensity component of the optical image and the SAR image are decomposed by JNNSR into common component and innovation components. Based on the non-negative property of the sparse coefficients, the innovation component of the SAR image is fused with the intensity component of the optical image. Finally, the fused result is obtained by performing inverse IHS transform. The experimental result shows that our method is superior to the traditional methods in terms of several universal quality evaluation indexes, as well as in the visual quality.