摘要
为解决可见光图像受光线、天气等影响而成像不清导致图像融合效果差的问题,对红外线与可见光图像提出一种基于夜视背景增强的融合方法,来提高图像融合后的效果.首先利用引导滤波对可见光图像内容进行增强,然后利用曲波变换将增强后的可见光图像和红外线图像分别进行分解.对低频部分采用基于能量保护和细节提取的融合方法,高频部分采用自适应参数的PCNN模型的融合规则;最后,利用曲波变换逆变换得到融合后的结果.实验结果表明所提方法在细节处理、保护边缘及源图像信息上都有良好的表现,由此提高了可见光图像照明条件不佳时的融合效果.
In order to improve the clarity of image fusion and solve the problem of poor image fusion effect caused by illumination and weather,this paper proposes a fusion method based on night vision background enhancement for infrared and visible images to improve the effect of image fusion.Firstly,guided filtering is used to enhance the content of visible image,and then curvelet transform is used to decompose the enhanced visible image and infrared image respectively.For the low frequency part,the fusion method based on energy protection and detail extraction is adopted.For the high frequency part,the fusion rules of the PCNN model with adaptive parameters is used.Finally,the fusion result is obtained by inverse transformation of curved wave transform.The experimental results show that the proposed method performs well in detail processing,edge protection and source image information,and improves the fusion effect under poor illumination conditions of visible images.
作者
张慧
常莉红
ZHANG Hui;CHANG Lihong(School of Mathematics and Computer Science,Ningxia Normal University,Guyuan Ningxia 756000)
出处
《宁夏师范学院学报》
2020年第7期45-52,共8页
Journal of Ningxia Normal University
基金
宁夏师范学院校级科研项目(NXSFYB2007).
关键词
图像融合
曲波变换
增强
引导滤波
多尺度分解
Image fusion
PCNN
Enhancement
Guided filtering
Multiscale decomposition
