Using Low-Rank Representation of Abundance Maps and Nonnegative Tensor Factorization for Hyperspectral Nonlinear Unmixing

Tensor-based methods have been widely studied to attack inverse problems in hyperspectral imaging since a image (HSI) cube can be naturally represented as third-order tensor, which perfectly retain the spatial information image. In this article, we extend linear tensor method nonlinear and propose low-rank unmixing algorithm solve generalized bilinear model (GBM). Specifically, parts of GBM both expressed tensors. Furthermore, structures abundance maps interaction are exploited by minimizing their nuclear norm, thus taking full advantage high correlation HSIs. Synthetic real-data experiments show that low rank our improve performance unmixing. A MATLAB demo work will available at https://github.com/LinaZhuang for sake reproducibility.