Infrared and Visible Image Fusion using Enhanced Thermal Image

During the day, visible image has excellent spatial resolution and clarity, and they are unreliable at night or when there is inadequate lighting. Target thermal radiation data can be seen in infrared pictures at night and in different types of weather. Infrared images, on the other hand, lack the presence of good textures details like that of visible image. Combining infrared and visible images aims to make up for the con of both imageries and can be effectively used in computer vision applications. The proposed approach is a heavyweight deep-learning approach. Encoder, fusion technique and decoder are the three main components of the method. This fusion method leads to the development of spatial based and channel based attention modules. Then the fusion approach is developed for every scale to merge these features. The experimental findings demonstrate that the suggested method performs better than other methods.