Research on the decomposition and fusion method for the infrared and visible images based on the guided image filtering and Gaussian filter

Abstract

For the fusion of the infrared and visible images, due to the infrared images having high contrast and big color difference, the traditional image decomposition methods cannot extract the high frequency information of the infrared image, so that the fused images tend to become blurred and confused. In this paper, a novel image decomposition method based on the guided image filtering and Gaussian filter is proposed, which can effectively extract small-scale texture detail information of the visible image and the large-scale edge information of the infrared image. In the fusion process, the large-scale edge image of the infrared image is used to be segmented and is used as the fused weights, which can prevent too much infrared information being injected into the fused image. Experimental results show that this method can effectively extract the infrared target object, so as to highlight the infrared target in the fused image and preserve the texture detail information of the visible image as much as possible. The proposed method is better than the traditional multi-scale decomposition based image fusion algorithms both in subjective and objective evaluation.