Fusion of multi-resolution visible image and infrared images based on guided filter

Abstract

Because of the poor lighting conditions at night time, visible images are often fused with corresponding infrared images for enhancement of the scenes in night vision. In this paper, a novel image fusion algorithm is presented for fusion of visible image and infrared image with different resolutions. The multiresolution image fusion is carried on by the following five steps: 1) different resolution images are transformed into the same resolution by use of wavelet transform; 2) to enhance the visibility of dark region content in the decomposed visible image, a novel night-vision enhancement method is presented based on guided filter; 3) the infrared image information is injected into the visible image through a multi-scale fusion approach based on guided filter; 4) inverse wavelet transform is used to achieve the fusion image; 5) to further improve the visibility of the fusion image, it is enhanced by use of an adaptive enhancement method.