Fusing Hyperspectral and Multispectral Images via Coupled Sparse Tensor Factorization | IEEE Journals & Magazine | IEEE Xplore

Fusing Hyperspectral and Multispectral Images via Coupled Sparse Tensor Factorization


Abstract:

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...Show More

Abstract:

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.
Published in: IEEE Transactions on Image Processing ( Volume: 27, Issue: 8, August 2018)
Page(s): 4118 - 4130
Date of Publication: 15 May 2018

ISSN Information:

PubMed ID: 29994767

Funding Agency:


References

References is not available for this document.