基于区域特征的遥感图像融合方法的改进

提出了一种基于小波变换的区域遥感图像融合方法的改进。对图像进行小波多分辨分析,以分解后的高频子图像的区域能量构造匹配度和融合算子,并给出了两个阈值,以便根据不同的特征构造不同的融合算子。对于低频部分采取加权平均的融合规则。并通过小波逆变换得到融合图像。根据主观目视判决和客观评价指标对融合结果进行了比较和分析,结果表明,本文的方法融合效果优于一般的融合方法,具有应用价值。

An Remote Image Fusion Method Based on Regional Features

A new regional remote image fusion method based-on wavelet transform is presented.Firstly,the image is processed by wavelet multiresolution analysis.The matching degree and fusion coefficient can be gained by regional energy of decomposed high frequency sub-image.Two thresholds are given in order to construct different fusion coefficient according to various features.Then,for low frequency sub-image,average coefficient is adopted.Finally,the fusion image is obtained by taking inverse wavelet transform.The performance of fusion scheme is evaluated and compared by objective and subjective factors.The experimental results show this fusion scheme is more effective than other fusion methods,and has application value.