科技创新与应用2025，Vol.15Issue(27)：42-45,4.DOI:10.19981/j.CN23-1581/G3.2025.27.009
基于NSCT和PCNN的红外与可见光图像融合方法
摘要
Abstract
Aiming at the problems of blurred boundaries and lost texture during multimodal fusion of infrared and visible images,a fusion method based on non-subsampled contourlet transform(NSCT)and pulse-coupled neural network(PCNN)is proposed to improve the fusion quality.First,two sets of source images are decomposed into high and low frequency subbands by using NSCT,and then fusion rules based on PCNN-are introduced to fuse the high and low frequency subbands.Finally,inversion reconstruction is applied to obtain the final fused image.Experimental results and objective evaluation show that the fusion method in this paper is superior to other comparison methods and can effectively retain infrared image features and visible light image texture information.Experimental results show that this method is superior to the comparison algorithm in terms of subjective visual quality and objective evaluation indicators(EN=7.031,VIF=0.719),and can effectively balance the contradiction between maintaining the saliency of infrared targets and extracting visible light texture details.关键词
图像融合/非下采样轮廓波变换/脉冲耦合神经网络/红外图像/可见光图像Key words
image fusion/non-subsampled contourlet transform/pulse-coupled neural network/infrared image/visible image分类
航空航天引用本文复制引用
周标胜,粟建波,何慧慧,周传明..基于NSCT和PCNN的红外与可见光图像融合方法[J].科技创新与应用,2025,15(27):42-45,4.基金项目
广西高校中青年教师科研基础能力提升项目(2023KY0225、2024KY0221、2025KY0255) （2023KY0225、2024KY0221、2025KY0255）
