Fusion of infrared and visible images based on image enhancement and feature extraction

In order to obtain night vision fusion image, which is more suitable for human visual perception, this paper proposes an infrared and visible image fusion method based on visible image enhancement and infrared feature extraction. Firstly, guided filtering and dynamic range compression are used to enhance the visible image adaptively. At the same time, the infrared pixel value is used as the index factor to transform the visible image exponentially to extract the infrared feature information. Finally, the hybrid multi-scale decomposition method based on guided filter is used to fuse the images. Experimental results show that the fused image has clear background details, outstanding thermal targets, and is superior to the compared methods, both in the visual quality and objective evaluation.