Nonlinear hyperspectral unmixing based on normalized P-linear algorithm

Abstract

This paper proposes a new supervised hyperspectral nonlinear unmixing method based on normalization. The main contribution is presented by reducing the overfitting of model and taking account to spatial correlation, using the normalization. The l ₂ -norm constraints of abundance and nonlinear coefficient are added to the P-Linear spectral mixing model. Moreover different positive parameters are given to control the trade-off between regularity and fitting. Finally, the problem can be expressed as a convex optimization problem, minimizing the cost function and the global optimum can be determined. The proposed method, abbreviated as NPLA (Normalized P-Linear Algorithm), is validated using hyperspectral synthetic and real datasets. The results indicate that the proposed method exhibits better performance on RMSE of abundance, reconstruction error and computed cost compared to other related classical hyperspectral nonlinear unmixing methods.