Semiblind Hyperspectral Unmixing in the Presence of Spectral Library Mismatches

• Published in: IEEE transactions on geoscience and remote sensing Vol. 54; no. 9; pp. 5171 - 5184
• Main Authors: Xiao Fu, Wing-Kin Ma, Bioucas-Dias, Jose M., Tsung-Han Chan
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.09.2016; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Compressive sensing (CS); Computer simulation; Dictionaries; dictionary mismatch; ell_{p} quasi-norm sparsity promoting; Hyperspectral imaging; Libraries; Multiple signal classification; Optimization; Regression; Remote sensing; robust dictionary pruning; semiblind hyperspectral unmixing (HU); Signal processing algorithms; Spectra; Spectral signatures
• ISSN: 0196-2892; 1558-0644
• DOI: 10.1109/TGRS.2016.2557340

The dictionary-aided sparse regression (SR) approach has recently emerged as a promising alternative to hyperspectral unmixing in remote sensing. By using an available spectral library as a dictionary, the SR approach identifies the underlying materials in a given hyperspectral image by selecting a small subset of spectral samples in the dictionary to represent the whole image. A drawback with the current SR developments is that an actual spectral signature in the scene is often assumed to have zero mismatch with its corresponding dictionary sample, and such an assumption is considered too ideal in practice. In this paper, we tackle the spectral signature mismatch problem by proposing a dictionary-adjusted nonconvex sparsity-encouraging regression (DANSER) framework. The main idea is to incorporate dictionary-correcting variables in an SR formulation. A simple and low per-iteration complexity algorithm is tailor-designed for practical realization of DANSER. Using the same dictionary-correcting idea, we also propose a robust subspace solution for dictionary pruning. Extensive simulations and real-data experiments show that the proposed method is effective in mitigating the undesirable spectral signature mismatch effects.