In the process of image fusion between visible and infrared images, the infrared image details are seriously lost, the edge is blurred and the visible image contrast is insufficient, etc., so an image fusion method combining the non sub sampled shear wave transform and guided filtering is proposed. Firstly, the visible and infrared images were decomposed by NSST to obtain the low frequency and high frequency sub bands. Secondly, guided filtering weighted sub band coefficients based on local area definition are used to fuse low frequency sub band coefficients, and improved guided filtering fusion is used to fuse high frequency sub band coefficients. Finally, NSST inverse transformation is used to obtain the fused image.Experimental results on different data sets show that this method is superior to other methods in information entropy, standard deviation, mutual information and other evaluation indexes, which verifies the effectiveness and superiority of the method proposed in this paper.
|