Superpixel-Based Collaborative and Low-Rank Regularization for Sparse Hyperspectral Unmixing

Sparse unmixing (SU) has been widely applied to remotely sensed hyperspectral images (HSIs) interpretation. Compared with traditional unmixing algorithms, SU does not need to extract pure signatures (endmembers) from the image. The endmember matrix is constructed by directly selecting spectra from a known library, which is used to estimate the fractional abundances associated with endmembers. This avoids the problem of extracting virtual endmembers without physical meaning. However, SU does not generally include spatial information, which may limit its performance. In order to address this limitation and include local spatial information, low-rank and sparse features in local regions can be exploited. In this article, we include spatial information in the traditional SU algorithm by extracting low-rank and spatial information based on superpixels and further propose an algorithm named superpixel-based collaborative sparse and low-rank regularization for SU (SCLRSU) to improve the performance of the traditional spatial regularization-based SU methods. In our proposed method, we combine superpixel segmentation and structural sparsity. Experiments are carried out on two simulated datasets and two real HSI datasets, and our results are compared with those obtained by traditional SU methods. Our results indicate that our newly proposed method provides very competitive performance.

Automated summary

Sparse unmixing (SU) is a method widely used for interpreting remotely sensed hyperspectral images. It avoids the need to extract pure signatures and directly selects spectra from a known library. However, SU generally lacks spatial information, which can be addressed by utilizing low-rank and sparse features in local regions.