A novel two-stage guided filtering based pansharpening method

Pansharpening methods generally inject the missing spatial details from a high spatial resolution panchromatic (PAN) image into the corresponding co-registered low spatial resolution multispectral (MS) images while preserving the spectral information. However, most of methods extract the details only from PAN image, which may lead to distortions in the sharpened results. Motivated by this, we present a novel two-stage guided filtering based pansharpening method. In the preliminary stage, an injection model based on multi-channel guidance filtering is designed to keep the spectral fidelity of MS imagery. Then a single channel guidance filtering based injection model is proposed to enhance the details in the second stage. The proposed method is tested and verified by GeoEye-1 satellite images. Qualitative and quantitative analyses demonstrate the superiority of the proposed method compared with some state-of-the-art guided filtering based pansharpening methods.