采用NSCT与FCM相结合的SAR和多光谱图像融合算法

合成孔径雷达（SAR）和多光谱（MS）图像的融合，有助于得到对观察对象的更好地视觉感知。但是，由于其内在成像机制上的差异，许多经典的方法已被证明不适合这一研究，因此本文提出了采用非下采样contourlet变换（NSCT）和模糊C均值聚类（FCM）相结合的图像融合算法。采用FCM对SAR图像进行分割，得到目标区域和背景区域；采用NSCT对SAR图像和多光谱图像进行分解，得到低频子带和高频方向子带；对于低频部分，不同分割区域采用不同的自适应融合准则进行融合；对于高频部分，采用区域块能量准则进行融合；最后，通过NSCT逆变换得到融合后图像。实验结果表明，该算法的融合图像能很好的保留SAR图像的目标信息和多光谱图像的光谱信息，融合效果优于大部分传统的融合算法。 

The SAR and multispectral image fusion algorithm combined with NSCT and FCM

Fusion of synthetic aperture radar (SAR) and multispectral (MS) images can contribute to a better visual perception of the objects observed. Unfortunately, many classical approaches have been proven to be unsuitable for this task due to their intrinsic differences in imaging mechanism, so a fusion algorithm based on non-subsampled contourlet transform(NSCT) and fuzzy c-means clustering(FCM) is proposed. The SAR image was segmented by FCM to extract the target area and background area ; the low-frequency sub-band and high-frequency directional sub-band were obtained by NSCT; for low-frequency part，different region was fused using different adaptive fusion criteria；for high-frequency part, regional block energy standard was used; finally, reconstructing images by NSCT inverse transform. Experimental results show that the fusion image can obtain target information of the SAR image and preserve spectral information of the multispectral image well. The proposed algorithm is better than most of the traditional fusion algorithms.