基于非线性变换与多尺度细节提升的红外图像增强算法  

INFRARED IMAGE ENHANCEMENT ALGORITHM BASED ON NONLINEAR TRANSFORMATION AND MULTI-SCALE DETAIL ENHANCEMENT

作　　者：唐守锋 仝光明 史经灿 史可 史凡 Tang Shoufeng;Tong Guangming;Shi Jingcan;Shi Ke;Shi Fan(School of Information and Control Engineering,China University of Mining and Technology,Xuzhou 221116,Jiangsu,China)

机构地区：[1]中国矿业大学信息与控制工程学院,江苏徐州221116

出　　处：《计算机应用与软件》2024年第10期247-253,共7页Computer Applications and Software

基　　金：国家重点研发计划项目(2016YFC0801800)。

摘　　要：在全暗或封闭的成像环境下,采集到的罐内红外图像存在分辨率低、对比度差以及噪声等问题。针对罐内红外图像的特征提出一种基于非线性变换与多尺度细节提升的红外图像增强算法,采用自适应非线性变换对红外图像亮度进行改善;然后通过多尺度滤波将图像多层次分解为基础层与细节层,分别使用不同方法进行处理后融合为细节图像,达到增强图像细节信息和对比度的效果;最后通过线性融合的方式对亮度图和细节图进行处理得到高质量的图像。实验结果表明该算法不仅使图像亮度得到了提升,也增强了图像对比度,突出了纹理细节,层次感得到明显的改善,视觉效果更佳。In a completely dark or enclosed imaging environment,the infrared image collected in the tank has problems such as low resolution,poor contrast,and noise.Aimed at the characteristics of the infrared image in the tank,an infrared image enhancement algorithm based on nonlinear transformation and multi-scale detail enhancement is proposed.The brightness of the infrared image was improved by adaptive nonlinear transformation,and the image was decomposed into base and detail layers through multi-scale filtering.The base layer and the detail layer were processed by different methods and merged into a detail image to achieve the effect of enhancing image detail information and contrast.The brightness map and the detail map were processed by linear fusion to obtain a high-quality image.Experimental results show that the algorithm not only improves the brightness of the image,but also enhances the image contrast,highlights the texture details,significantly improves the sense of hierarchy,and has better visual effects.

关 键 词：图像增强 细节提升 对比度增强 红外图像 黑暗条件 油泥识别 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]