Context:

Systems that acquire hyperspectral (HS) images have opened a wide field of applications in different areas, such as remote sensing and computer vision applications. However, hardware restrictions may limit the performance of such applications because of the low spatial resolution of obtained hyperspectral images. In the state-of-the-art, the fusion of a HS image with low spatial resolution panchromatic (PAN) or multispectral (MS) images with high spatial resolution has been efficiently employed to computationally improve the resolution of the HS source. The problem of fusing images is traditionally described as an ill-posed inverse problem whose solution is obtained assuming that the high spatial resolution HS (HR-HS) image is sparse in an analytic or learned dictionary.

Method:

This paper proposes a non-locally centralized sparse representation model on a set of learned dictionaries to spatially regularize the fusion problem. Besides, we consider the linear mixing model that decomposes the measured spectrum into a collection of constituent spectra (endmembers) and a set of corresponding fractions (abundance) maps to take advantage of the intrinsic properties and low dimensionality of HS images. The spatial-spectral dictionaries are learned from the estimated abundance maps exploiting the spectral correlation between abundance maps and the non-local self-similarity in the spatial domain. Then, an alternating iterative algorithm is employed to solve the fusion problem conditionally on the learned dictionaries.

Results:

After using real data, the results show that the proposed method outperforms the state-of-the-art methods under various quantitative metrics: RMSE, UIQI, SAM, ERGAS, PSNR, and DD.

Conclusions:

This paper proposes a novel fusion model that includes a non-local Sparse representation of abundance maps by using spectral unmixing. The proposed model obtains better fused images than traditional fusion approaches based on sparcity.

Financing:

Project Vicerrectoría de Investigación y Extensión of Universidad Industrial de Santader (code VIE 2521).