Generative adversarial network-based remote sensing image fusion method, system and terminal

Abstract

The invention discloses a generative adversarial network-based remote sensing image fusion method, and the method comprises the steps: employing a difference operator to extract the spatial structureinformation of an original panchromatic image, and sampling the original multispectral image; splicing the spatial structure information and the sampled multispectral image in a feature domain to obtain a sample image; inputting the sample image into a generator of a generative adversarial network to generate a fused image; and inputting the fused image and the real image into a discriminator of the generative adversarial network for discriminating and distinguishing, establishing an adversarial rule and a fusion objective function between the generator and the discriminator, and optimizing the fused image. According to the remote sensing image fusion method based on the generative adversarial network disclosed by the invention, the spatial structure information of the original panchromatic image is reserved by adopting the differential operator, and the spectral information of the original low-resolution multispectral image is reserved by adopting the sampling method, so that the lossof detail information in the fusion process is effectively reduced; in addition, a confrontation rule and a fusion objective function are established between the generator and the discriminator, so that the fusion effect is greatly optimized.

Description

technical field [0001] The invention relates to the technical field of remote sensing image processing, in particular to a remote sensing image fusion method, system and terminal based on a generative confrontation network. Background technique [0002] With the continuous advancement of modern science and technology, remote sensing technology is widely used in disaster early warning, military detection, marine meteorological prediction and land resource classification and other fields. As an information carrier for detecting targets, remote sensing obtains information through various sensors. However, in the prior art, due to the limitation of the hardware technology of remote sensing satellites, remote sensing satellites can only obtain high-resolution panchromatic images and low-resolution images. The multispectral image of the multispectral image is obtained by fusion method to obtain a high resolution and high quality multispectral image. [0003] At present, remote se...

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to provide a remote sensing image fusion method to solve the problem of insufficient spectral information and structural information change of the fused image, retain the spatial structure information of the panchromatic image, reduce the loss of detail information in the fusion process, and retain the original The spectral information of low-resolution multispectral images optimizes the effect of fusion

Images