Maritime Infrared and Visible Image Fusion Based on Refined Features Fusion and Sobel Loss

Abstract

Infrared (IR) and visible image fusion has become an important technology for maritime environment awareness. In this study, we employed refined features fusion and Sobel loss for maritime IR and visible image fusion. First, we used the encoder in Densefuse net to transform the image to be fused from the pixel domain to the feature domain. Then, the features’ information was accurately measured, and the refined features were fused and sent to the decoder to reconstruct the fused images. Mixed loss, commonly employed in image fusion, eliminates the effect of different losses but also introduces hyperparameters. We innovatively used Sobel loss to measure the input and fused images to reduce the hyperparameters in the loss function. Finally, experiments were performed, and our algorithm achieved good fusion results in the qualitative and quantitative evaluations.

Keywords

• maritime image
• infrared and visible image fusion
• feature fusion
• Sobel loss