Infrared and visible light image fusion method

Abstract

The invention belongs to the technical field of image processing, and particularly relates to an infrared and visible light image fusion method. According to the infrared and visible light image fusion method based on the hybrid l1-l0 decomposition model and the auto-encoder, the hybrid l1-l0 decomposition model is used to take the image decomposition result as the output of the double-layer auto-encoding network, so that the double-layer auto-encoding network has self-contained layer decomposition capability. Image features are decomposed into base layer features and detail layer features, and different fusion strategies are customized for different layers, so that more texture information and heat radiation information can be maintained. And the l1 norm strategy is utilized to compensatethe neglected thermal radiation information of saliency detection, so that the robustness of base layer fusion is improved. The network adopts an end-to-end mode to simplify the training process, andthe model complexity is reduced. Through matrix operation, the time consumption of feature fusion processing is reduced, and the response speed of a fusion framework is further improved.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a fusion method of infrared and visible light images. Background technique [0002] Infrared and visible light fusion is an important branch of image fusion technology. Infrared technology has been widely used in biology, medical, military and security fields. Although infrared images can provide good thermal radiation information to help people detect and diagnose, their value at the application level is greatly reduced due to their low resolution and lack of a large amount of texture information. Therefore, people hope to use image fusion technology to combine visible light images The texture spatial information is injected into the infrared image so that the fused image not only retains the infrared radiation information but also holds rich texture information, thus improving its application value. [0003] At present, the most common infrared and visible...

AI Technical Summary

Problems solved by technology

In these CNN-based fusion methods, the general strategy is to use the results of the last layer of the feature extraction network as image features. This strategy will lose a lot of information contained in the middle layer of the network and affect the fusion results.

Images