Constrained Nonnegative Matrix Factorization for Robust Hyperspectral Unmixing

Hyperspectral unmixng (HU) is an essential step for hyperspectral image (HSI) analysis. In real HSI, there often are abnormal fluctuations existing in specific bands, which can be described as sparse noise. This type of corruption will seriously disrupt the hyperspectral image quality, causing extra difficulties during unmixing process. However, the influence of sparse noise is often ignored by existing unmixing methods, which leads to the reduction of robustness and accuracy for HU tasks. Therefore, we propose a new unmixing model which takes noise corruption into consideration. By designing and imposing constraints considering the sparsity of noise, properties of endmember and abundance on nonnegative matrix factorization (NMF), the proposed method can resist the sparse noise and achieve more robust and accurate unmixing results. Adequate experiments have been conducted on both synthetic and real hyperspectral data. And the results confirm the superiority of proposed method compared to state-of-the-art methods.