采用非抽样轮廓波的红外与可见光图像融合

Infrared and visible images fusion using non-subsampled contourlet transform

提出了一种基于非抽样轮廓波变换的红外与可见光图像融合算法。该算法首先利用非抽样轮廓波变换对输入图像进行多尺度、多方向稀疏分解,有效地表达了图像的高维奇异信息;然后,为了弥补基于像素的图像融合方法的不足,在变换域通过邻域一致性测度的计算,实现了变换系数的局部自适应融合。实验结果表明,所提出的算法既可保持可见光图像的光谱信息,又可有效获取红外图像的热目标信息。

A fusion algorithm for infrared and visible images using Non-Subsampled Contourlet Transform（NSCT） is proposed.By using NSCT,the input images are decomposed into multi-scale and multi-dierction subbands to represent the high dimensional singularity of images.Then,in order to overcome the shortcoming of pixel-based fusion,this algorithm realizes the local adaptive fusion via Neighborhood Homogeneity Measurement （NHM）.The simulation results show that the presented algorithm can not only hold spectrum information of the visual image, but also get hot object information of the infrared image effectively