针对灰度图像融合的分辨率低及现有的彩色图像融合方法融合的图像色彩不自然、不符合人的视觉感受的特点，在此提出一种基于Snake模型的区域检测和非下采样轮廓波变换(NSCT)的红外与彩色可见光图像融合的方法。首先对彩色可见光图像进行亮度、色度和饱和度(IHS)颜色空间变换提取亮度分量，并用Snake模型对红外图像的目标区域进行检测；然后对亮度分量和目标替换的红外图像应用NSCT分解，对所得到的高频系数采用像素点“绝对值和取大”、低频系数采用基于“亮度重映射技术”的加权融合规则进行融合；通过对融合系数进行NSCT逆变换获得融合图像的亮度分量，最后运用颜色空间逆变换得到融合图像。实验结果表明，所提出的融合方法既能保持可见光图像的高分辨率和自然色彩，又能准确保留红外图像中检测出的目标信息，获得视觉效果较好、综合指标较优的融合图像。

An infrared and color visible image fusion method based on Snake model region detection and non-subsampled contourlet transform(NSCT) is presented. In this method, first of all, the luminance component is extracted by using IHS(intensity, hue, saturation) color space conversion for color visible images and the target region of infrared images is detected by adopting Snake model. Then NSCT decomposition is utilized for the luminance component and target replaced infrared image. Image fusion is done by using the largest pixels absolute value sum for the high frequency coefficient and the weighted fusion rules based on brightness mapping technology for the low frequency coefficient. NSCT inverse transform is adopted to obtain the brightness of the image fusion for the fusion coefficients. Finally, the color space inverse transformation is used to acquire fusion images. Experimental results show that the proposed fusion method can not only maintain a high resolution and natural colors of the visible image, but also accurately retain the target information detected in the infrared image. Compared with other methods, fusion images with a better visual effect and comprehensive indicator can be achieved.