Infrared and visible light image fusion method based on phase consistency and target enhancement

Abstract

The invention provides an infrared and visible light image fusion method based on phase consistency and target enhancement. The method comprises the following steps: firstly, performing multi-scale decomposition on a source image by using a Laplace pyramid to obtain high and low frequency sub-bands; secondly, for the high-frequency sub-band, extracting an image feature map by adopting phase consistency, and calculating a weight matrix by using the feature map so as to obtain a fused high-frequency sub-band; for the low-frequency sub-band, firstly constructing an initial weight matrix accordingto the significance, and then adding the weight matrix of the infrared low-frequency sub-band and a correction term calculated by the low-frequency sub-band feature map to obtain a final infrared low-frequency sub-band weight matrix, thereby obtaining a fused low-frequency sub-band; and finally, obtaining a fused image through inverse transformation reconstruction of the Laplacian pyramid. According to the method, the edge and texture information of the fused image can be effectively reflected, the significance of the infrared target is well reserved, and meanwhile, the method has good contrast and visual effect.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to an infrared and visible light image fusion method based on phase consistency and target enhancement. Background technique [0002] The fusion of infrared (IR) and visible light images plays an important role in military and civilian applications, such as target detection, surveillance, and intelligence gathering. Infrared imaging sensors can capture thermal radiation emitted by objects and are less affected by dark or harsh weather conditions . However, the obtained IR images usually lack sufficient background details of the scene. In contrast, visible images usually contain more detail and texture information and have corresponding infrared images with higher spatial resolution. Infrared and visible light image fusion can produce synthetic images that provide more information for human observation or computer vision tasks. [0003] Fusion methods based on multi-scale...

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problems of loss of texture details, poor contrast and loss of infrared target saliency in the traditional Laplacian pyramid fusion method, the present invention provides an infrared and visible light image fusion method based on phase consistency and target enhancement, which mainly includes the following step:

Images