Combining Enhancement and Fusion for Low-Light Visible and Infrared Image

Abstract

Visible and infrared fusion aims to create a fused image that encompasses not only complex texture details and target-specific information but also facilitates advanced visual analyses. However, existing fusion algorithms rarely focus on the fusion of visible and infrared images in low-light environments. Therefore, in this article we propose a enhancement and fusion network for low-light visible and infrared that processes images in two stages. In the first stage, we correct the color shift of the visible light image caused by abnormal-light source and enhance the brightness of the image. In the second stage, we use the fusion network to fuse the enhancement results of the first stage with infrared, and use the loss function to constrain the network. Finally, we explore the performance of our fusion results for object detection tasks. Experimental results show that our fusion results have obvious brightness enhancement effect, high color contrast, obvious texture details and target information, and also achieve good performance in target detection tasks.