A New Algorithm for Infrared and Visible Light Image Fusion

Abstract

The invention relates to a novel fusion algorithm of infrared and visible light images, comprising the steps of: using non-subsampling contour transformation to perform multi-scale transformation on pre-registered infrared images and visible light images respectively, to obtain bandpass corresponding to infrared images and visible light images respectively low-pass component and low-pass component; use the method of deep neural network to guide the image depth feature to fuse the low-pass component to obtain the low-pass component fusion image; use the method of taking the maximum modulus to compare the band-pass component, and select the maximum value as the band-pass The weight of the component fusion, and according to the weight to fuse the band-pass component to obtain the band-pass component fusion image; the low-pass component fusion image and the band-pass component fusion image are reconstructed by the inverse transformation of the non-subsampling contour transformation, and the final fused image. The present invention can preserve the main information of the source image in the result image to the greatest extent, and no noise and artifacts will appear in the fused image.

Description

technical field [0001] The invention relates to the technical field of image fusion, in particular to a novel infrared and visible light image fusion algorithm. Background technique [0002] Fields such as military, navigation, stealth weapon detection, and medical imaging often require multiple different imaging bands to monitor a target scene for a more comprehensive visual understanding. Using cameras with different bands to acquire images can provide rich and detailed scene information. However, in specific observation scenarios, in order to display more detailed information, the imaging advantages of multiple image bands can be combined. [0003] Image fusion techniques have been extensively studied in the past few decades. The multi-scale transformation method based on Laplacian and contrastive pyramid was first proposed for image decomposition. The image fusion method based on steerable pyramid and expectation maximization is superior to the traditional fusion metho...

AI Technical Summary

Problems solved by technology

[0009] In order to overcome the problems existing in the prior art, improve the fusion effect of infrared and visible light images, and reduce the artificial noise and artifacts of the fused images, the present invention provides a new infrared and visible light image fusion algorithm. A new fusion framework combining non-subsampling contour transformation method and deep residual network can give full play to the decomposition advantages of image multi-scale transformation, and at the same time, it can also exert the feature extraction ability of deep residual neural network

Images