基于加权小波分析的遥感图像融合算法  

Remote Sensing Images Fusion Algorithm Based on Weighted Wavelet Analysis

作　　者：莫才健[1] 田健榕 武锋强[1] 陈莉[1] 邹强[1] MO Caijian;TIAN Jianrong;WU Fengqiang;CHEN Li;ZOU Qiang(College of Environment and Resource, Southzvest University of Science and Technology, Mianyang 621010, Sichuan Province, China;College of .Journalism ＆ Communication , Jilin University, Changchun 130012, China)

机构地区：[1]西南科技大学环境与资源学院,四川绵阳621010 [2]吉林大学新闻与传播学院,长春130012

出　　处：《吉林大学学报（理学版）》2018年第3期617-624,共8页Journal of Jilin University:Science Edition

基　　金：国家自然科学基金重点项目基金(批准号:41401598);四川省教育厅科研项目(批准号:18ZA0489);西南科技大学博士基金(批准号:14ZX7128)

摘　　要：提出一种基于加权小波分析的遥感图像融合算法.首先在光照色度饱和度空间上提取多光谱图像的光照强度分量,对光照强度分量进行主成分分析获得修正的光照强度,再将修正的光照强度与小波分析高频区域进行加权融合,最后进行小波分析与光照色度饱和度空间逆变换获得遥感图像的最终融合结果.该方法有效解决了在低频空间分辨率与高频空间分辨率的图像融合过程中,小波分析方法丢弃低频分量易产生分块模糊现象,且主成分分析方法易产生光谱图像信息域失真的问题.在不同场景遥感图像的融合上进行仿真实验,结果表明,该算法在一定程度上解决了图像融合后边缘模糊、融合结果中出现模糊块状阴影等问题,并在清晰度、纹理细节和真实性上获得了较大提升,且能针对不同的融合需求调整合适的加权系数,使遥感图像的融合达到最佳效果.在光照色度饱和度空间,加权小波分析进一步提升了遥感图像融合的效果,不仅充分表达了各种遥感图像的细节,而且能较好地保留原始光谱信息.We proposed a remote sensing images fusion algorithm based on weighted wavelet analysis.Firstly,we extracted the illumination intensity component of multispectral images in the illumination chroma saturation space,and made a principal component analysis of the illumination intensity component to get the corrected illumination intensity.Secondly,the weighted fusion was carried out by corrected illumination intensity and wavelet analysis for the high frequency region.Finally,the final fusion results of remote sensing images were obtained by inverse transform of wavelet analysis and illumination chroma saturation space.This algorithm effectively solved the problems of block blurred phenomenon caused by the way of wavelet analysis to discard low frequency components and distortion of information domain produced by principal component analysis in the process of image fusion with low spatial resolution and high spatial resolution.We carried out simulation experimentson the fusion of remote sensing image in different scenes.The results show that the proposed algorithm can solve some common problems such as blurring of edge after image fusion and fuzzy block shadow appearing in fusion result.It is greatly improved in clarity,texture details and authenticity,and can adjust the appropriate weighting coefficient for different fusion needs,so that the fusion of remote sensing images can achieve the best effect.The weighted wavelet analysis further improves the effect of remote sensing image fusion,not only fully expresses the details of various remote sensing images,but also preserves the orginal spectral information better.

关 键 词：HSI颜色空间 主成分分析 离散小波分析 遥感图像融合 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]