Method and system for constructing fusion model of infrared image and visible light image

Abstract

The invention provides a method and a system for constructing a fusion model of an infrared image and a visible light image, the model comprises a generator and a discriminator, and the method comprises the following steps: enabling the generator to adopt a gradient path to extract detail information of the image and adopt an intensity path to extract contrast characteristics of the image; fusing the images obtained by the two paths through a cascade method to obtain a fused image; using two discriminators to process the fused image, wherein one discriminator extracts contrast information of the fused image and the infrared image by taking the infrared image as real data, and the other discriminator extracts detail information of the fused image by taking the visible light image as real data; and completing the construction of a fusion model through continuous adversarial training between the generator and the discriminator. The fusion image obtained by the scheme of the invention is more in line with the visual perception of people, and can contain more detail information and obvious contrast characteristics.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a method and system for building and fusing fusion models of infrared images and visible light images. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] Image fusion is an enhancement technique that fuses images from different types of sensors to produce comprehensive, information-rich images for subsequent processing. In particular, the fusion technology of infrared and visible light images has been widely used to enhance human visual perception, object detection and object recognition. [0004] For the same application scenario, image sensors with different bands can reflect different scene information. Image fusion of different spectral bands is one of the research hotspots in the field of computer vision and image proce...

AI Technical Summary

Problems solved by technology

[0008] 1. The deep learning method is only used for feature extraction in image fusion, but the whole framework still uses the traditional network;

[0009] 2. The traditional GAN ​​only uses one discriminator for confrontation training, only retains the information of one of the source images, and loses a lot of information of the other source image, resulting in unclear images and insufficient retained information in the final fusion result. Complete and other issues

Images