Fusing Hyperspectral and Multispectral Images via Coupled Sparse Tensor Factorization

• Published in: IEEE transactions on image processing Vol. 27; no. 8; pp. 4118 - 4130
• Main Authors: Li, Shutao, Dian, Renwei, Fang, Leyuan, Bioucas-Dias, Jose M.
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.08.2018
• Subjects: coupled sparse tensor factorization; Dictionaries; Estimation; fusion; Hyperspectral imaging; Sparse matrices; Spatial resolution; Super-resolution; Tensile stress
• ISSN: 1057-7149; 1941-0042
• DOI: 10.1109/TIP.2018.2836307

Fusing a low spatial resolution hyperspectral image (LR-HSI) with a high spatial resolution multispectral image (HR-MSI) to obtain a high spatial resolution hyperspectral image (HR-HSI) has attracted increasing interest in recent years. In this paper, we propose a coupled sparse tensor factorization (CSTF)-based approach for fusing such images. In the proposed CSTF method, we consider an HR-HSI as a 3D tensor and redefine the fusion problem as the estimation of a core tensor and dictionaries of the three modes. The high spatial-spectral correlations in the HR-HSI are modeled by incorporating a regularizer, which promotes sparse core tensors. The estimation of the dictionaries and the core tensor are formulated as a coupled tensor factorization of the LR-HSI and of the HR-MSI. Experiments on two remotely sensed HSIs demonstrate the superiority of the proposed CSTF algorithm over the current state-of-the-art HSI-MSI fusion approaches.