Hyperspectral image super-resolution method based on mixed attention network fusion

Abstract

The invention discloses a hyperspectral image super-resolution method based on mixed attention network fusion. The method comprises the following steps: acquiring a hyperspectral low-resolution image and a corresponding hyperspectral high-resolution image, and forming training data; constructing a hyperspectral image super-resolution basic model; training the hyperspectral image super-resolution basic model by adopting the training data to obtain a final hyperspectral image super-resolution model; obtaining a to-be-processed hyperspectral image; and processing the to-be-processed hyperspectral image by using the hyperspectral image super-resolution model to complete the super-resolution process of the hyperspectral image. According to the invention, the hybrid attention network is adopted to improve the network performance, mutual learning loss is adopted to ensure that each network has mutual supervision and learning capabilities, and finally, an adaptive integration module is adopted to fuse output images of the hybrid attention network. Therefore, the invention is better in effect, higher in reliability and more excellent in performance.

Description

technical field [0001] The invention belongs to the field of image processing, in particular to a hyperspectral image super-resolution method based on hybrid attention network fusion. Background technique [0002] Hyperspectral images contain not only the spatial information of the target scene, but also rich spectral information, and have been widely used in many fields such as civil, military, medical, and computer vision. However, due to the hardware limitations of hyperspectral imaging sensors, hyperspectral images contain rich spectral resolution, but their spatial resolution is very low. Therefore, it is particularly important to improve the spatial resolution of hyperspectral images by studying super-resolution algorithms for hyperspectral images. [0003] Traditional hyperspectral image super-resolution methods mainly fall into the following two categories: fusion strategy-based hyperspectral image super-resolution algorithms and single-image-based hyperspectral ima...

AI Technical Summary

Problems solved by technology

However, most of the current hyperspectral image super-resolution networks only consider the hyperspectral image super-resolution of a single network, and do not consider the influence between super-resolution networks.

In addition, most existing networks ignore the multi-scale information of feature maps, resulting in certain distortions in the spectral information of the reconstructed hyperspectral image, and the loss of some spatial structure details.

Images