Multispectral image classification method based on adaptive feature fusion residual network

By using an adaptive feature fusion residual network, the problem of spectral and spatial feature extraction and fusion in multispectral images is solved, achieving more efficient and accurate multispectral image classification and improving the model's representation and generalization capabilities.

CN121962772APending Publication Date: 2026-05-01JIANGSU UNIV OF SCI & TECH
0 Cites 0 Cited by

Patent Information

Application Number
CN202610259974.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-03-04
Publication Date
2026-05-01

AI Technical Summary

Technical Problem

Existing technologies struggle to efficiently and accurately extract and classify spectral and spatial features from multispectral images, and deep learning models suffer from gradient vanishing and insufficient feature fusion issues in multispectral data processing.

Method used

An adaptive feature fusion residual network is adopted. Spectral and spatial features are extracted separately through a dual-path feature extraction backbone network and then weighted and fused through an adaptive feature fusion module. The feature extraction and fusion process is optimized by combining a channel attention mechanism and a residual structure.

Benefits of technology

It achieves more efficient and accurate multispectral image classification, improves the model's representation and generalization capabilities, and can better utilize the spectral-spatial joint information of multispectral data to improve classification accuracy.

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

Abstract

The invention provides a multispectral image classification method based on an adaptive feature fusion residual network, and belongs to the technical field of computer vision and remote sensing image processing. The method comprises the following steps: firstly, preprocessing an original multispectral image; then, a novel adaptive feature fusion residual network model is constructed, the core of the model comprises a dual-path feature extraction backbone network, and spectral features and spatial context features are extracted respectively; a self-adaptive feature fusion module is introduced, multi-level features from double paths are dynamically learned and fused through a channel attention mechanism, and optimal integration of spectral information and spatial information is achieved; and finally, completing pixel-level or image-level classification by using the fused advanced features. According to the method, the problems of insufficient utilization of spectrum-space joint features of multispectral data and weak model generalization ability of a traditional method are effectively solved, and the precision and robustness of multispectral image classification are remarkably improved.
Need to check novelty before this filing date? Find Prior Art