Incorporating spatial information into hyperspectral unmixing procedures has been shown to have positive effects, due to the inherent spatial-spectral duality in hyperspectral scenes. Current research works that consider spatial information are mainly focused on the linear mixing model. In this paper, we investigate a variational approach to incorporating spatial correlation into a nonlinear unmixing procedure. A nonlinear algorithm operating in reproducing kernel Hilbert spaces, associated with an ℓ1 local variation norm as the spatial regularizer, is derived. Experimental results, with both synthetic and real data, illustrate the effectiveness of the proposed scheme.
@article{arxiv.1310.8612,
title = {Nonlinear unmixing of hyperspectral images using a semiparametric model and spatial regularization},
author = {Jie Chen and Cédric Richard and Alfred O. Hero},
journal= {arXiv preprint arXiv:1310.8612},
year = {2013}
}