Superresolution of hyperspectral images using backpropagation neural networks

Hyperspectral technology has introduced a new perspective in remote sensing applications but suffers from low spatial resolution. A new spatial-spectral data fusion technique based on spectral mixture analysis and super-resolution mapping for spatial resolution enhancement of hyperspectral imagery is proposed in this paper. To this end a linear mixture model and a fully constrained least squares based unmixing algorithm are applied for spectral unmixing of the hyperspectral imagery and the resulted fractional images are processed based on a spatial-spectral information correlation model through a super-resolution mapping technique. To validate the performance of the method, experiments are carried out on real images. The obtained results validate the effectiveness of the method. It doesn't need any a priori information of the scene or secondary high resolution source of data, and is low in terms of computational cost.