Efficient Two-Phase Multiobjective Sparse Unmixing Approach for Hyperspectral Data

In our previous work, a two-phase multiobjective sparse unmixing (Tp-MoSU) approach has been proposed, which settled the regularization parameter issues of the regularization unmixing methods. However, Tp-MoSU has limited performance in identifying the real endmembers from the highly noisy data in the first phase and cannot effectively exploit the spatial-contextual information in the second phase because of the similarity measure it used. To settle these two problems, a composite spectral similarity measure is first constructed by fusing the spectral correlation angle and the Euclidean distance. It is used instead of the Frobenius norm to measure the unmixing residuals in the first phase because it considers both the shape and amplitude discrepancy between two spectra simultaneously. Then, the L-2,L-infinity norm is used instead of the l(2) norm to measure the unmixing residuals in the second phase, and the initialization, recombination, mutation, and local search strategies are also elaborately redesigned to help reduce this new objective, based on which the unmixing tasks of all pixels in a hyperspectral image can be completed at once. Therefore, this new measure facilitates the estimation of the abundances as a whole, and thus, the spatial-contextual information can be better exploited to improve the estimated abundances. Besides, the time efficiency for abundance estimation is also greatly improved. Experimental results demonstrate that the proposed method (termed as Tp-MoSU+) outperforms Tp-MoSU in both of the two phases under heavy noise and outperforms the tested regularization algorithms in estimating the abundances.

Automated summary

A new two-phase multiobjective sparse unmixing method was proposed in this study, which addressed the issues of identifying real endmembers from highly noisy data and effectively utilizing spatial-contextual information by constructing a composite spectral similarity measure. Experimental results showed that this method outperformed existing methods in both phases and abundance estimation under heavy noise.