Low-light image enhancement method for extracting and fusing local and global features

The invention discloses a low-light image enhancement method for extracting and fusing local and global features, and relates to the technical field of image processing. According to the method, a built BrigtFormer network structure is utilized, cross convolution and a self-attention mechanism are organically unified, two advantages of local extraction and global dependence are considered at the same time, features are fused from two dimensions of space and channel by utilizing a feature equalization fusion unit, and the method comprises the following steps. According to the method, the local and global features of the image are extracted and fused at the same time, a new low-illumination image enhancement network model is established, the model fully combines local details and global information learned by the convolution and self-attention module to effectively enhance the low-illumination image, and through a new local-global feature fusion module, the low-illumination image can be effectively enhanced. Th