Visible and infrared image fusion based on visual saliency detection

Abstract

Visible and infrared image fusion is widely adopted in navigation, object recognition and smart city. In this paper, we use the saliency object detection method to fusion the visible and infrared images. In consideration of the properties of the different type of image, we design two different visual saliency object detection methods to fuse the coefficients of detail image layers and coarse image layers. Then we can reconstruct the fused image from those coefficients. The experimental results indicate that the proposed fusion algorithm conforms to the human vision characteristics and has a strong comparability and effectiveness in both objective and subjective evaluation.