Infrared and visible light image fusion method with regional attention

Abstract

Infrared and visible light image fusion aims at fusing information such as thermal radiation and texture details in the same scene by using information complementarity, so that the fused image content is more comprehensive and clearer, and human eye observation, subsequent tasks and the like are facilitated. The steps of image fusion are generally feature extraction, feature fusion and image reconstruction. The invention provides a fusion method with regional attention. Firstly, an encoder is used for extracting high-dimensional features, then a fusion strategy with significant region attention is designed for fusing the features, and finally, a decoder is used for reconstructing an image. The invention aims to solve the problem of image fusion in a scene with insufficient illumination. The result shows that good texture details of the visible light image can be fully reserved, and the infrared image is utilized to carry out content supplementation on the underexposure area. In addition, the highlighted display area in the source image is still kept highlighted in the fused image due to the attention to the salient area, and the good effect that the advantages of the infrared image and the visible light image are complementary is achieved.

Description

technical field [0001] The invention belongs to the technical field of image processing, and particularly relates to an infrared and visible light image fusion method with regional attention. Background technique [0002] With the steady development of hardware and software industries, the use of sensors to collect information, as well as the ability to transmit and process information is also increasing. In this context, vision-based sensors are widely used because they can provide rich environmental information. A single type of sensor only has the information characteristics of a certain aspect, which cannot satisfy the comprehensive description of the monitoring environment. Therefore, multi-sensor systems have begun to receive more and more attention and applications. The multi-source sensor imaging system completely fills the vacancy of the insufficient image expression ability of a single sensor. At present, image fusion technology has played a significant role in r...

AI Technical Summary

Problems solved by technology

To improve the quality of detail information and sharpen the edges of hot objects, they also introduce detail loss and edge enhancement loss

Due to the difficulty of GAN training, this method fails to obtain good fusion quality, and cannot highlight salient information

Images