现代电子技术2024，Vol.47Issue(2)：100-104,5.DOI:10.16652/j.issn.1004-373x.2024.02.019
一种基于U2-Net的红外热成像与可见光图像融合方法
Method of infrared thermal imaging and visible light image fusion based on U2-Net
谢迅 1程为彬1
作者信息
- 1. 长江大学 地球物理与石油资源学院, 湖北 武汉 430100
- 折叠
摘要
Abstract
In order to solve the problem of low resolution and high cost of infrared thermal imaging,a method for detecting prominent targets in infrared thermal imaging and visible light images using the U2-Net structure model is proposed by combining with the characteristics of high resolution and low cost of visible light images.For the prominent target in the image,by means of image cropping,contour extraction,affine transformation,centroid calculation,size transformation,match targeting and fusion,etc.,the target object is fused in the infrared image and the visible light image.The experimental results show that the fusion of the target object in the low-resolution infrared thermal imaging and the high-resolution visible light image can effectively improve the visibility of the target object in the overall image by this method.关键词
红外热成像/可见光图像/图像融合/U2-Net/显著目标检测/图像匹配定位Key words
infrared thermal imaging/visible light image/image fusion/U2-Net/salient target detection/image matching positioning分类
信息技术与安全科学引用本文复制引用
谢迅,程为彬..一种基于U2-Net的红外热成像与可见光图像融合方法[J].现代电子技术,2024,47(2):100-104,5.
