Infrared and Visible Image Fusion Method Based on NSCT Combined with Guided Filtering

To address the problems of information loss and incomplete display of edge and texture detail information in existing image fusion methods, this paper proposes an infrared and visible image fusion method based on NSCT combined with guided filtering. The method decomposes the visible source image and infrared source image by NSCT algorithm to obtain low-frequency and high-frequency subbands; according to the characteristics of information contained in low-frequency and high-frequency subbands, a weighted averaging rule based on guided filtering is proposed to fuse low-frequency subbands, and a fusion rule based on regional standard deviation and pixel value taking larger combined with Gaussian adaptive is designed to fuse high-frequency subbands; finally, the image is reconstructed by NSCT inversion to obtain the final fused image. The experimental results show that the proposed method outperforms other methods in several evaluation indexes, has better edge retention, higher contrast and sharpness, and better visual effects.