Objectives The objective of infrared and visible image fusion in the all-weather road scenes is to generate fusion images that contain rich textures and significant goals. However, due to the influence of light conditions and harsh weather factors, the existing infrared and visible image fusion algorithm is difficult to achieve the ideal effect.

Methods In response to this issue, an infrared and visible image fusion network suitable for all -weather road scenes was proposed. First, we designed an illumination loss function that can guide the intensity distribution of the background texture and the intensity of significant goals in the adaptive network. Second, the introduction of the Scharr gradient to improve the calculation accuracy of the gradient of texture loss, and restrict the fusion image to retain more delicate texture details. Finally, we designed the second order residual block based on the Resblock structure to enhance the ability to integrate network extraction of strong and weak texture features of images.

Results Comparison and generalization experiments on MFNet, RoadScene, and TNO data sets show that the proposed method is better than other advanced methods in subjective visual effects and objective indicators.

Conclusions Therefore, the three optimized designs the proposed can improve the fusion effect of visible and infrared images.