Panchromatic and multispectral image fusion method based on deep learning

Abstract

The invention provides a panchromatic and multispectral image fusion method and system based on deep learning. The method comprises the following steps: acquiring a panchromatic image and a multispectral image to be fused; inputting the panchromatic image and the multispectral image into a pre-trained image fusion model to obtain a fused remote sensing image. According to the scheme, the deep neural network can be fully utilized, the spatial structure information of the image is highlighted, and the image style is adjusted by utilizing the constructed branch spectrum adjustment network, so that the fused remote sensing image not only has high spatial resolution, but also can well reserve the specific style information of a specific satellite.

Description

technical field [0001] The disclosure belongs to the technical field of remote sensing image processing, and in particular relates to a method for fusion of panchromatic and multispectral images based on deep learning. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art. [0003] Earth remote sensing satellites usually provide two different types of images, panchromatic images with high spatial and low spectral resolution and multispectral images with low spatial and high spectral resolution. At present, due to technical limitations, satellite sensors acquire panchromatic images and multispectral images, and cannot directly acquire multispectral images with high spatial and hyperspectral resolution. [0004] The inventors found that there is a remote sensing image fusion method through a deep neural network in existing methods, but the existing tradit...

AI Technical Summary

Problems solved by technology

At present, due to technical limitations, satellite sensors acquire panchromatic images and multispectral images, and cannot directly acquire multispectral images with high spatial and hyperspectral resolution.

[0004] The inventor found that there is a remote sensing image fusion method through a deep neural network in existing methods, but the existing traditional fusion of panchromatic images and multispectral images based on a deep neural network usually trains a model for each satellite, and requires a large number of For the different styles of images taken by satellites with different sensors, separate training data is required, and the fusion of different styles of images from different sensors requires training different network models, resulting in low model training efficiency. At the same time, in the absence of a large amount of training data The fusion model trained under the premise cannot guarantee the fusion quality

Images