Infrared and Visible image fusion method based on Dual-Graph Latlent Low-Rank Representation Nested With Target-Enhanced Multiscale Transform

Infrared and visible image fusion are widely used in target tracking, detection, and recognition. In order to improve the accuracy of image contour extraction, low brightness and contrastlack of detailed contour information and poor visibility. In this paper, we propose an infrared and visible image fusion method based on dual-graph latent low-rank representation and target-enhanced. The method first considers the local structural information in images of different modalitiesThe image is then decomposed using the dual-graph latent low-rank representation to obtain the corresponding base part and saliency part. To extract more efficient fusion features, target-enhanced multi-scale transform decomposition is applied to the basic information. Additionally, the salient part and base part are fused with different fusion strategies, resulting in higher resolution and lower noise than other current methods.