The Color Fusion of Infrared and Visual Images Based on NSCT

Abstract

In the night vision fusion, traditional methods, such as the wavelet transform, always suffer from the problems of shift-variant, limited direction. In order to obtain a more ideal fused image, this paper proposes a new night vision fusion scheme based on NSCT (nonsubsampled contour let transform). And we can convert the fused grayscale image into the color image by YUV color space, ultimately generating the color fused image. The experimental results demonstrate that the proposed method not only keep abundant details of the background, but also improves the contrast and detect ability of the target object. And the color based on color transfer algorithm closes to natural color, superior to the traditional method such as false color, it's more conducive to identify the target and the environment for people.