Image super-resolution reconstruction method and system based on channel constraint multi-feature fusion

Abstract

The invention discloses an image super-resolution reconstruction method and system based on channel constraint multi-feature fusion, and belongs to the field of super-resolution image reconstruction. The method comprises the steps: acquiring high-spatial-resolution hyperspectral image pairs, low-spatial-resolution hyperspectral image pairs and high-spatial-resolution multispectral image pairs in the same scene to construct a training set; constructing a double-channel super-resolution network, wherein the system comprises: a feature extraction module which is used for extracting spatial-spectral features from low-spatial-resolution hyperspectral and high-spatial-resolution multispectral images in the same scene at the same time, a feature fusion module which is used for fusing the spatial information of the multispectral images and the spectral information of the hyperspectral images in the same scene, and an image reconstruction module which is used for reconstructing to obtain a reconstructed image; training the network until the change rule of each element in the corresponding spectral vectors of the reconstructed image and the original image is consistent; and acquiring a low-spatial-resolution hyperspectral image and a high-spatial-resolution multispectral image in a scene to be reconstructed, and inputting the image into the trained network to obtain a reconstructed super-resolution hyperspectral image.

Description

technical field [0001] The invention belongs to the field of super-resolution image reconstruction, and more particularly relates to an image super-resolution reconstruction method and system based on channel-constrained multi-feature fusion. Background technique [0002] In the field of remote sensing images, there must be a certain trade-off between spectral and spatial detail information. In order to ensure the integrity of spectral band information, part of its spatial detail information has to be sacrificed. However, this will bring greater difficulty to subsequent advanced tasks. The application of hyperspectral images is limited. Therefore, improving the spatial quality of the image while ensuring the spectral resolution, so that it can restore the scene information to the greatest extent, is the focus and difficulty of current hyperspectral research. [0003] There are usually two ways to improve the spatial resolution of hyperspectral images: one way is to improve ...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the defects and improvement needs of the prior art, the present invention provides an image super-resolution reconstruction method and system based on channel-constrained multi-feature fusion. Problems such as distortion and difficulty in image reconstruction when the super-resolution multiple is high

Images