Infrared and visible light image fusion method based on detail enhancement channel attention

Abstract

The invention relates to an infrared and visible light image fusion method based on detail enhancement channel attention, and belongs to the technical field of feature extraction and image fusion. Themethod comprises the following steps: 1, cutting an infrared image and a visible light image into image blocks with the same size and cascading the image blocks; 2, enabling the cascaded image to sequentially pass through a convolution layer, a batch regularization layer and an activation function to obtain a high-dimensional feature map; 3, enabling the high-dimensional feature map to pass through a DECA module to obtain an information-enhanced high-dimensional feature map; 4, repeating the steps 2 and 3 for Q times, and further performing information enhancement on the high-dimensional feature map; 5, performing operation on the high-dimensional feature map of which the information is further enhanced through the convolution layer, the batch regularization layer and the activation function, and outputting a fusion feature map; 6, calculating a loss function, and updating parameters of the convolution layer and a full connection layer; and 7, fixing parameters of the convolution layer and the full connection layer, and fusing the images. According to the method, brightness information can be extracted from the fused image, a highlight target in the image is highlighted, and meanwhile a large amount of detail information is reserved.

Description

technical field [0001] The invention relates to an infrared and visible light image fusion method based on detail enhanced channel attention, and belongs to the technical field of feature extraction and image fusion. Background technique [0002] Image fusion technology is the process of combining data from different sensors / modalities of the same scene into a single image. The fused image can carry more comprehensive information than the source image. A large number of image fusion methods have been proposed for different applications, such as computer vision, photography, and medical imaging. Fusion images based on infrared and visible light images can be used for target recognition or detection. How to make the fusion image not only contain details and texture information in visible light images, but also contain high-brightness targets in infrared images, so as to combine multi-mode Preserving state information in an image is the main problem of current research. [0...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to address the technical defects of the existing infrared and visible light image fusion methods such as the loss of detail texture information and the inconspicuous infrared detection target, and propose an infrared and visible light image fusion method based on detail enhancement channel attention

Images