光谱与空间局部相关的SVR影像融合方法

A Robust SVR Image Fusion Method Based on Local Spectral and Spatial Correlation

针对合成变量比(synthetic variable ratio,SVR)融合方法可能存在的颜色偏差问题,提出一种基于光谱与空间相关的遥感影像融合方法。该方法利用全色影像与多光谱影像的光谱与空间相关特性,采用局部优化策略模拟全色波段,能够有效地减少融合影像的光谱扭曲。选择WorldView-2等卫星的全色和多光谱影像进行融合试验,采用目视和量化指标进行评价,并与现有流行算法进行对比,验证了本文方法的优越性。

To solve the potential color distortion problem of SVR （synthetic variable ratio） method, an improved fusion method based on local spectral and spatial correlation is proposed. The proposed method uses spectral and spatial correlation characteristics and local optimization strategy to simulate panchromatic image, which can effectively reduce the spectral distortion of fused image. To assess the quality of the proposed method, several satellite images such as WorldView-2 panchromatic and multispectral images were used. Comparing with some existed popular techniques, visual and quantitative analysis proved that the proposed method can significantly improve the fusion quality.