Infrared and visible image fusion method based on second-order attention mixed features

By adopting a fusion method based on second-order attention hybrid features, the problem of fusion of infrared and visible light images in complex scenes is solved, achieving efficient fusion in complex environments, preserving the details and structural information of the images, and improving the fusion effect.

CN120976034BActive Publication Date: 2026-07-24BEIJING INST OF TECH
2 Cites 0 Cited by

Patent Information

Application Number
CN202511009726.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-07-22
Publication Date
2026-07-24
Estimated Expiration
2045-07-22

AI Technical Summary

Technical Problem

Existing infrared and visible light image fusion methods are difficult to adapt to information changes in complex scenes, ignore the internal correlation of features, resulting in structural differences between the fused image and the original image, and fail to effectively utilize the deep relationships between features at different scales, resulting in distortion and artifacts.

Method used

A fusion method based on second-order attention hybrid features is adopted. Through dual-scale feature extraction, dual-stream second-order attention fusion module and dynamic feature upsampling module, global and local features of infrared and visible light images are adaptively integrated to construct second-order channel and spatial attention units, and feature reconstruction is performed by combining depthwise separable convolution.

Benefits of technology

It achieves efficient fusion of infrared and visible light images in complex environments, preserving pixel intensity and texture details, producing realistic output results with reduced artifacts, and improving the fusion effect and human visual perception quality.

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

Abstract

The application provides an infrared and visible light image fusion method based on second-order attention mixed features, first-order and second-order statistics of an infrared image and a visible light image are input, global features and local features of the infrared image and the visible light image are adaptively integrated, so that the fusion image obtains stronger feature expression, meanwhile, pixel intensity and texture details are retained, comparable contrast is maintained while more realistic edges are realized, the output result retains rich edge and texture information transmitted by the input image, has fewer artifacts, and better meets human visual perception; compared with other infrared and visible light image fusion algorithms based on deep learning, the application has better fusion effect.
Need to check novelty before this filing date? Find Prior Art