ABSTRACT
Sparse spectral unmixing assumes the constituent spectra (endmembers) can be selected from a given spectral library and seeks sparse combination coefficients (abundances) of endmembers to reconstruct the input hyperspectral image. The existing methods extensively exploit the prior information of abundances and design various regularizations on abundances. In this paper, taking advantage of the low-rank property of the reconstructed image, we propose a generic unmixing model by incorporating a low-rank regularization on the data reconstruction term to the traditional sparse unmixing models. The low-rank reconstruction regularization plays a role in attenuating noise and errors, therefore helps our models achieve better sparse recovery results while preserving details. We illustrate two models which combine the low-rank reconstruction term with sparse and joint sparse abundances regularizers, respectively. A series of simulation and real-world data are used to evaluate the performances of the proposed models, and their results are compared with that obtained by state-of-the-art algorithms. Both visual comparison and quantitative evaluation are presented to show the effectiveness of our methods.
Acknowledgements
We would like to thank M. D. Iordache, J. M. Bioucas-Dias, A. Plaza, and J. Huang for sharing their codes for algorithms of SUnSAL, CLSUnSAL, SUnSAL-TV, and JSpBLRU, as well as thank W. Tang and F. Zhu for providing their experimental data sets.
Disclosure statement
No potential conflict of interest was reported by the author.