Nonlinear unmixing of hyperspectral images using a semiparametric model and spatial regularization
This work addresses hyperspectral image analysis for remote sensing applications, but it is incremental as it extends existing nonlinear methods by adding spatial regularization.
The paper tackled the problem of nonlinear unmixing in hyperspectral images by developing a variational approach that incorporates spatial correlation using an ℓ1 local variation norm as a spatial regularizer, resulting in effective performance demonstrated through experiments with synthetic and real data.
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 $\ell_1$ local variation norm as the spatial regularizer, is derived. Experimental results, with both synthetic and real data, illustrate the effectiveness of the proposed scheme.