Generative adversarial network-based remote sensing image strip denoising method and system

Through the method based on the generative adversarial network, the spatial and temporal characteristics of banded noise in remote sensing images are extracted, and the problem of poor results in the prior art when dealing with irregular and dynamic banded noise is solved, and the effect of efficient denoising and image detail retention is achieved.

CN119648573AActive Publication Date: 2025-03-18STATE OCEANIC ADMINISTRATION EAST CHINA SEA INFORMATION CENTER (STATE OCEANIC ADMINISTRATION EAST CHINA SEA ARCHIVES) +1
8 Cites 4 Cited by

Patent Information

Application Number
CN202510175042.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-02-18
Publication Date
2025-03-18
Estimated Expiration
2045-02-18

AI Technical Summary

Technical Problem

The prior art has poor results when dealing with irregular banding or dynamic banding noise, and lacks the ability to model the law of time evolution, resulting in low consistency of multi-time phase images.

Method used

Using a generative adversarial network-based method, the spatial distribution characteristics and temporal dynamic characteristics of banded noise are extracted by constructing an image detection model, and the denoising image is generated by combining the generator and the discriminator, and the final processing is performed through the image fusion algorithm.

Benefits of technology

It realizes efficient removal of wide bands, thin bands and dynamic band noise, retains image details and spectral information, and improves the accuracy and consistency of multi-scene remote sensing image processing.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention relates to the technical field of remote sensing image processing, in particular to a remote sensing image strip denoising method and system based on a generative adversarial network, and provides the following scheme: collecting remote sensing image data; constructing an image detection model, extracting spatial distribution characteristics of the stripe noise through the first processing network to generate an abnormal node marking graph, and extracting time dynamic characteristics of the stripe noise through the second processing network to generate a time characteristic mapping graph; a generative adversarial network is constructed, a generator performs joint optimization according to space and time characteristics to generate a de-noised image, and a discriminator performs authenticity verification on the de-noised image and feeds back parameters of the optimization generator; and finally, through an image fusion algorithm, carrying out fusion processing on the de-noised image and the original noiseless area to generate an optimized remote sensing image. The method can efficiently remove wide strip, thin strip and dynamic strip noise, retains image details and spectral information, and is suitable for multi-scene remote sensing image processing.
Need to check novelty before this filing date? Find Prior Art