Resolution enhancement of hyperspectral images using a learning-based super-resolution mapping technique

A fast and efficient spatial-spectral fusion method for resolution enhancement of hyperspectral imagery is proposed in this paper. A linear mixture model and fully constrained least squares based unmixing algorithm are applied for spectral unmixing of the hyperspectral imagery and the resulted fractional images are processed using a spatial-spectral information correlation model through a learning-based super-resolution mapping technique. To validate the performance of the method, experiments are carried out on real images. The obtained results validate the reliability of the technique. The main advantages of the proposed method include its autonomous nature so that it doesn't need any high resolution secondary source of data, its acceptable performance, and its low computational cost which makes it favorable for realtime target recognition and tracking applications.