基于Curvelet变换联合灰度测算因子的遥感图像融合算法  

Remote Sensing Image Fusion Algorithm Based on Curvelet Transform andGrayscale Measurement Factor

作　　者：杨巧曼 Yang Qiaoman(Shaanxi College of Communications Technology)

机构地区：[1]陕西交通职业技术学院,西安市710018

出　　处：《勘察科学技术》2024年第4期6-10,64,共6页Site Investigation Science and Technology

基　　金：国家自然科学基金青年基金项目(编号:61806023)。

摘　　要：该文在遥感图像融合研究中,为获取具有良好光谱特征与细节突出的遥感图像,利用Curvelet变换设计灰度测算因子。首先通过HSV变换剥离出多光谱图像的亮度分量V;采用Curvelet变换获取图像系数;接着利用图像的区域方差和均值融合低频系数,利用高频系数的灰度特征构造灰度测算因子融合高频系数;最后通过Curvelet反变换求取V分量的更新值V^(~),求取融合遥感图像。实验结果显示:该文给出的低频系数融合因子可获得光谱特征较好的融合低频系数;研究的灰度测算因子对求取细节丰富的融合高频系数有较好的效果。In order to obtain remote sensing images with good spectral features and prominent details,this paper designs a grayscale measurement factor based on the Curvelet transform for remote sensing image fusion.Firstly,the brightness component V is extracted from the multispectral image through HSV(Hue,Saturation,Value)transformation.Secondly,the image coefficient is obtained by using the Curvelet transform.Thirdly,based on the area variance and mean features of image,a low-frequency coefficient fusion operator is established,and by using the grayscale features of high-frequency coefficients to construct a grayscale measurement factor,the richness of image details is measured,and a high-frequency coefficient fusion operator is formed.Finally,under the influence of the Curvelet inverse transform,the updated componentV~of the brightness component V is obtained.The experimental results show that the low-frequency coefficient fusion factor provided in this paper can obtain fused low-frequency coefficients with good spectral characteristics.The grayscale calculation factor studied has a good effect on obtaining fusion high-frequency coefficients with rich details.

关 键 词：遥感图像融合 灰度测算因子 CURVELET变换 HSV变换 区域方差特征 灰度特征 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]