基于深度神经网络的红外与可见光图像融合算法研究  

Research on Infrared and Visible Light Image Fusion Algorithm Based on Deep Neural Networks

作　　者：赵何超 何洋楠 肖佳欢 ZHAO Hechao;HE Yangnan;XIAO Jiahuan(Xi'an University of Technology,Xi'an 710021,China)

机构地区：[1]西安工业大学,陕西西安710021

出　　处：《数字通信世界》2024年第10期34-36,共3页Digital Communication World

摘　　要：该文提出并优化了一种基于深度神经网络的红外与可见光图像融合算法,采用感知损失和对抗性训练两种优化策略。经实验验证,优化算法在图像质量上超越传统方法。感知损失提高了融合图像的清晰度和语义信息,对抗性训练增强了真实感和细节保留。这一研究为红外与可见光图像融合领域引入了先进的深度学习方法,为相关领域的技术应用提供了有力支持。This article proposes and optimizes an infrared and visible light image fusion algorithm based on deep neural networks,using two optimization strategies:perceptual loss and adversarial training.Through experimental verification,the optimization algorithm surpasses traditional methods in image quality.Perceived loss improves the clarity and semantic information of fused images,while adversarial training enhances realism and detail preservation.This study introduces advanced deep learning methods into the field of infrared and visible light image fusion,providing strong support for technical applications in related fields.

关 键 词：图像融合 深度神经网络 感知损失 对抗性训练 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]