Hyperspectral image super-resolution based on a Linear and Intimate Mixing Model
- Resource Type
- Conference
- Authors
- Zha, Yuchen; Liu, Hongyi
- Source
- 2023 13th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS) Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS), 2023 13th Workshop on. :1-4 Oct, 2023
- Subject
- Computing and Processing
Signal Processing and Analysis
Tensors
Superresolution
Signal processing
Visual effects
Numerical models
Spatial resolution
Hyperspectral imaging
Hyperspectral images
multispectral images
super-resolution
nonlinear unmixing
- Language
- ISSN
- 2158-6276
Hyperspectral super-resolution (HSR) aims to obtain a high spatial resolution hyperspectral image (HR-HSI) by fusing a high spatial resolution multispectral image (HR-MSI) and a low spatial resolution hyperspectral image (LR-HSI). In this paper, a HSR model with a linear and intimate mixing model is proposed. The unmixing model is combined with Hapke model to provide more flexible endmembers. Furthermore, the HR-HSI image is represented by tensor form as well as unmixing view, resulting in a nonlinear and physical interpretation HSR method. Numerical experiments show that the proposed HSR method shows better performance compared with other methods.