Remote sensing image scene classification method and system based on double-filtering cooperation

By using a dual-filter collaborative optimization module to process remote sensing image feature maps, the contradiction between noise suppression and edge preservation in remote sensing image scene classification is resolved. This achieves efficient background noise filtering and edge enhancement, thereby improving the accuracy and anti-interference capability of remote sensing image scene classification.

CN122265858AActive Publication Date: 2026-06-23耕宇牧星(北京)空间科技有限公司
6 Cites 0 Cited by

Patent Information

Application Number
CN202610253195.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-03-03
Publication Date
2026-06-23
Estimated Expiration
2046-03-03

AI Technical Summary

Technical Problem

Existing remote sensing image scene classification methods tend to lose key edge information when suppressing background noise, resulting in insufficient feature discrimination power and difficulty in distinguishing scene categories with similar textures but different structures.

Method used

A dual-filter collaborative approach is adopted, combining Gaussian blur filtering and Gaussian Laplace filtering. The remote sensing image feature map is processed through a dual-channel collaborative optimization module to purify background noise and enhance the edge structure of ground features. The zero-crossing detection characteristic of Gaussian Laplace filtering is used to accurately capture edge features.

Benefits of technology

It significantly improves the accuracy and anti-interference ability of remote sensing image scene classification, and can retain the edge structure of key ground objects while filtering out redundant background textures, generating a clean and clear scene representation, and improving the classification accuracy of complex scenes.

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

Abstract

The invention discloses a remote sensing image scene classification method and system based on double-filtering cooperation, and provides a double-filtering cooperation optimization module for solving the problem that background noise suppression and key ground feature edge structure maintenance are difficult to consider when a remote sensing image is processed in the prior art. In the module, a Gaussian filtering smooth channel is introduced to suppress unstructured high-frequency background noise, and meanwhile, a Gaussian Laplacian edge enhancement channel is introduced to accurately capture and enhance key geometric structure information such as ground feature contours and the like; through feature fusion, position coding, a state space model and a double-activation gating mechanism, the multi-scale feature map is optimized and reconstructed, and scene representation with a high signal-to-noise ratio and a clear structure is generated. The module is integrated into a remote sensing image scene classification model, and focus loss is adopted for training, so that the classification precision and robustness in a complex texture interference scene can be remarkably improved.
Need to check novelty before this filing date? Find Prior Art