Pansharpening scheme using spatial detail injection-based convolutional neural networks

Pansharpening produces a high spatial-spectral resolution pansharpened image by combining multispectral (MS) and panchromatic (PAN) images. In the traditional multi-resolution analysis (MRA) method, detailed PAN images are extracted by transformation methods that are injected into MS images. This gives spatial and spectral distortions in the pansharpened image. These distortions can be reduced in the pansharpened image by the correct matching of the PAN detail image component. This correct matching is possible by the convolutional neural network (CNN)-based models. This paper obtains the detailed image component using the CNN models. This CNN model extracts the PAN detail image that is suitable for the MRA-based pansharpening scheme which significantly reduces the spatial and spectral distortions. It is demonstrated by qualitative and quantitative analysis applied on GeoEye-1 and IKONOS satellite images and shows the effectiveness of the proposed scheme.