结合双边滤波Retinex和图像融合的图像去雾方法  

Image defogging method combining bilateral filtering Retinex and image fusion

作　　者：向朝 XIANG Zhao(Zhongnan Engineering Corporation Limited,Power China,Changsha Hunan 410014,China)

机构地区：[1]中国电建集团中南勘测设计研究院有限公司,湖南长沙410014

出　　处：《北京测绘》2023年第11期1525-1530,共6页Beijing Surveying and Mapping

摘　　要：针对传统的去雾方法对无人机有雾图像进行去雾时存在细节丢失严重、去雾效果差等问题,本文提出了一种结合双边滤波视网膜反应(Retinex)算法和图像融合的图像去雾方法。首先,利用双边滤波Retinex精确计算入射分量,对亮度分量进行双边滤波Retinex处理。其次,对两个色彩空间处理后的影像进行图像融合。最后,本文以两景无人机有雾图像为实验数据进行实验,结果表明,本文方法的标准差和信息熵等指数整体上升,能获得细节与色彩较好的去雾影像。Aiming at the problems of serious detail loss and poor defogging effect of traditional defogging methods for defogging foggy images of unmanned aerial vehicles(UAVs),this paper proposes an image defogging method that combines bilateral filtering Retinal algorithm and image fusion.Firstly,the incident component is accurately calculated using bilateral filtering Retinex,and the luminance component is processed by bilateral filtering Retinex.Secondly,image fusion is performed on the processed images in two color spaces.Finally,two views of UAV with foggy images were utilized for experiments.Results show that the proposed method present increased indices such as standard deviation and information entropy,and obtained de-fogged images with better details and colors.

关 键 词：无人机影像 双边滤波 视网膜反应算法 图像融合 图像去雾 

分 类 号：P231[天文地球—摄影测量与遥感]