Sparse unmixing based denoising for hyperspectral images

Abstract

Until recently, hyperspectral image denoising was considered as a prior step to applications such as classification, detection, or unmixing. However, unmixing has been recently shown to also provide denoising due to its inherent property of representing pixels in terms of pure material signatures and their abundances. It is possible to eliminate sensor-induced or atmospheric noise by unmixing based denoising, by not including these noise effects in the endmember signatures. Up until now, only spectral unmixing, and in a more recent paper spectral unmixing after spatial preprocessing, have been utilized for hyperspectral denoising. This letter proposes the use of spatial - spectral sparse unmixing for hyperspectral denoising. Sparse unmixing has the advantage of circumventing dimensionality detection, while the use of spatial processing in the sparse regression further enhances the unmixing and denoising performance. The proposed approach provides enhanced denoising and inpainting performance with respect to previously proposed unmixing based change detection approaches.