针对遥感图像影像分辨率低的问题，提出了一种新的基于非下采样Contourlet变换的图像融合算法。该算法首先通过IHS变换对多光谱图像进行RGB-IHS颜色空间转换，然后利用非下采样Contourlet变换和模糊推理加权融合规则将强度分量与全色图像进行融合，最后用拉伸后的灰度融合图像替换原来的强度分量，并通过IHS逆变换得到最终的融合图像。实验结果表明，该方法在抑制光谱信息扭曲和提高图像清晰度等客观评价参数上均优于其他多分辨率分析方法，且克服了传统融合方法中存在的融合图像模糊、抗噪能力差的缺点。

As for low resolution of remote sensing images，a novel fuzzy reasoning fusion algorithm by nonsubsampled contourlet transform was proposed.Firstly，the multi-spectral image is converted from RGB space to IHS space through IHS transform.Next，with nonsubsampled contourlet transform and weighted average fusion rules based on fuzzy reasoning，the component intensity and panchromatic image are merged into a grayscale image.Finally，the stretched grayscale fused image replaces the original component intensity，and then the final fused image is achieved by inverse IHS transform.The experimental results show that the proposed method not only can obtain better effect on restraining spectral information distortion and enhancing space definition than other multi-resolution analysis methods，but also avoid some of the well-known problems in common fusion processes such as blurring effects and high sensitivity to noise.