A Proposed Fully Constrained Least Squares for Solving Sparse Endmember Fractions with Linear Spectral Mixture Model

In this paper, we propose a proposed fully constrained least squares (p-FCLS) for spectral unmixing, which assumes that the endmember with the absolute maximum negative abundance by least squares is the disturbing endmember and that can be ignored subsequently, then the other endmembers are returned in the iteration until the abundance of all endmembers are non-negative. To evaluate the effectiveness of the proposed algorithm, hyperspectral data samples by ASD Field spectrometer and the EO-1 Hyperion image are employed. The results illustrate that p-FCLS could reduced time consumption and is more accurate in unmixing hyperspectral mixed spectral and pixel than fully constrained least squares (FCLS) and normalized non-negative matrix factorization (NNMF).