Hyperspectral image fusion method combining spectral unmixing prior and learnable degradation constraint

Abstract

The invention discloses a hyperspectral image fusion method combining spectral unmixing prior and learnable degradation constraint, and the method comprises the steps: applying an unmixing model to a hyperspectral image, and building a degradation relation between high-resolution abundance and low-resolution abundance; the low-resolution abundance and the high-resolution abundance are optimized in combination with a hyperspectral image unmixing process; constructing a spatial degradation network and a spectral degradation network to learn a degradation relationship between images, wherein the spatial degradation network can adapt to input of abundance and hyperspectral images at the same time; constructing a residual block to optimize an intermediate image, and learning finer features; the network loss function is an L1 norm. The method has excellent performance when being applied to full-color image and hyperspectral image fusion or multispectral image and hyperspectral image fusion.

Description

technical field [0001] The invention relates to a hyperspectral image fusion technology, in particular to a hyperspectral image fusion method combining spectral unmixing prior and learnable degradation constraints. Background technique [0002] Low-resolution hyperspectral images (LRHS) have dozens or even thousands of spectral bands, which can capture the detailed spectral information of objects, with a large spectral range and rich spectral information. High-resolution multispectral images (HRMS) have less spectral information than hyperspectral images, but have higher spatial resolution, which can provide spatial information for hyperspectral images to generate high-resolution hyperspectral (HRHS) images with good spatial and spectral resolution. [0003] The deep learning network uses the structure of the multi-layer neural network to perform multiple linear and nonlinear transformations on the original signal, thereby extracting rich signal features and applying them t...

AI Technical Summary

Problems solved by technology

The network achieves better results with fewer layers, but directly learns the mapping relationship without using the correlation between images

Images