Band selection in RKHS for fast nonlinear unmixing of hyperspectral images

TL;DR

This paper introduces a band selection method in reproducing kernel Hilbert spaces to significantly reduce computational costs in nonlinear hyperspectral unmixing, achieving two orders of magnitude speed-up without performance loss.

Contribution

The paper proposes a novel band selection strategy in RKHS that drastically reduces processing time for nonlinear unmixing of hyperspectral images.

Findings

Complexity reduced by two orders of magnitude

Unmixing performance maintained

Effective band selection in RKHS

Abstract

The profusion of spectral bands generated by the acquisition process of hyperspectral images generally leads to high computational costs. Such difficulties arise in particular with nonlinear unmixing methods, which are naturally more complex than linear ones. This complexity, associated with the high redundancy of information within the complete set of bands, make the search of band selection algorithms relevant. With this work, we propose a band selection strategy in reproducing kernel Hilbert spaces that allows to drastically reduce the processing time required by nonlinear unmixing techniques. Simulation results show a complexity reduction of two orders of magnitude without compromising unmixing performance.