摘要
IHS变换法对多光谱图像和高分辨图像进行融合会丢失较多的光谱信息 ,本文利用进化策略来求解IHS变换法中光谱强度分量的最佳变换问题 ,经过变换后的光谱强度分量与多光谱图像的光谱强度分量和高分辨图像都具有较强的相关性 ,经过IHS反变换后可以得到同时具有较好的空间分辨率和光谱信息的融合图像 .实验结果表明 。
A new technique is developed for the data fusion of two images. Two spatially registered images with differing spatial resolutions and color content are merged by modifying the spectral intensity component and then reconstructing the fusion image by means of the inverse IHS transform. The intensity component is modified by a best transform curve, which is obtained by evolutionary strategies, and is closer to the intensity component of multispectral image and is closer to the high resolution image in the meantime. Experimental comparisons show that the proposed method performs better in preserving spatial resolutions and color content than that of traditional IHS transform technique and wavelet transform fusion method.
出处
《电子学报》
EI
CAS
CSCD
北大核心
2001年第10期1388-1391,共4页
Acta Electronica Sinica
基金
多传感器系统数据融合算法研究 (No .98J.6 .1DZ0 1 1 1 4 )
关键词
图像融合
IHS变换
进化策略
图像处理
Curve fitting
Evolutionary algorithms
Image processing
Mathematical transformations
