Infrared Image Super-Resolution Reconstruction Method and System Based on Convolutional Neural Networks

By training a convolutional neural network with a hybrid loss function, and combining multi-scale feature fusion and residual connections, the problem of insufficient network structure in infrared image super-resolution reconstruction is solved, generating high-resolution infrared images with high clarity and rich detail.

CN121073798BActive Publication Date: 2026-05-26BEIJING DONGYU HONGDA TECH CO LTD
3 Cites 0 Cited by

Patent Information

Application Number
CN202511218605.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-08-28
Publication Date
2026-05-26
Estimated Expiration
2045-08-28

AI Technical Summary

Technical Problem

Existing convolutional neural networks suffer from shallow network structures, limited receptive fields, lack of multi-scale feature fusion, and single information transmission paths in infrared image super-resolution reconstruction. This results in blurred edges and distorted textures in the reconstructed high-resolution images, making it difficult to accurately restore image details, especially in complex target scenes.

Method used

A convolutional neural network is trained using a hybrid loss function, combining adversarial and perceptual loss terms. Through multi-scale feature fusion and attention mechanism weighting, high-resolution infrared images are generated using upsampling structures and residual connections, ensuring the preservation of detail information and image quality.

Benefits of technology

The generated high-resolution infrared images have rich details and clear structure, improving the resolution and detail reproduction of the images and meeting the reconstruction needs of complex target scenes.

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

Abstract

A method and system for super-resolution reconstruction of infrared images based on convolutional neural networks, relating to the field of electronic digital data processing, is disclosed. The method includes: inputting a low-resolution infrared image into a preset convolutional neural network to obtain multi-layer feature maps of the low-resolution infrared image; scaling the feature maps of different layers in the multi-layer feature maps according to a preset ratio and then stitching and fusing them to obtain a fused feature map; generating feature vectors from the fused feature map using global average pooling, and transforming the feature vectors using a fully connected layer to obtain attention weights; weighting the attention weights with the fused feature map to obtain an enhanced feature map; and performing upsampling reconstruction processing on the enhanced feature map using an upsampling structure, introducing a residual connection structure during the upsampling reconstruction process to generate a high-resolution infrared image. Implementing this method generates high-resolution infrared images with more detail.
Need to check novelty before this filing date? Find Prior Art