An Approach for Fusion of Thermal and Visible Images

We present a novel architecture to fuse thermal and visible images using deep learning algorithms. As infrared images contain higher information, an object can be distinguished from its background due to radiation difference and work well in all conditions such as bad weather and night time. Contrast to that, visible images provide texture information with high spatial resolution or visual context of the objects. Therefore, it is advisable to fuse infrared and visible images which can combine the advantages of thermal radiation information and detailed texture information. Compared to traditional methods of convolutional networks, our proposed network extracts more salient features from individual images by introducing depthwise convolution in the network which reduces more number of parameters. Then after, features from two different sources are fused and an image is reconstructed by decoder network. We compare our proposed method with other state-of-the-art methods, which outperforms on qualitative and quantitative assessment.