基于加权近红外图像融合的单幅图像除雾方法  

Single Image Defogging Method Based on Weighted Near-InFrared Image Fusion

作　　者：朱珍[1] 黄锐 臧铁钢[3] 卢世军 ZHU Zhen;HUANG Rui;ZANG Tie-gang;LU Shi-jun(School of Information Technology,Guangdong Engineering Polytechnic College,Guangzhou 510520,China;School of Computer Science&Technology,Beijing Institute of Technology,Beijing 100081,China;School of Mechatronics,Nanjing University of Aeronautics and Astronautics,Nanjing 210016,China;School of Geography and Planning,Sun Yat-Sen University,Guangzhou 510275,China)

机构地区：[1]广东工程职业技术学院信息工程学院,广州510520 [2]北京理工大学计算机学院,北京100081 [3]南京航空航天大学机电学院,南京210016 [4]中山大学地理科学与规划学院,广州510275

出　　处：《计算机科学》2020年第8期241-244,共4页Computer Science

基　　金：国家自然基金项目(61274085);广东省科学技术厅项目(2014A010103008,2016B090918021);广东省教育厅重点科研平台和科研项目(2018GKQNCX009);广东省教育厅项目品牌专业项目(2016gzpp031)。

摘　　要：传统图像除雾方法存在无雾区域中图像对比度过高的问题,导致在某些情况下生成的图像视觉效果不够自然。为了得到自然清晰的除雾图像,提出了一种基于加权近红外(Near-InFrared,NIR)图像融合的新型单幅图像除雾方法,通过将NIR图像的细节成分融合到同一场景的可见光图像中来恢复图像对比度,并使用透射图对NIR图像进行加权,从而防止无雾区域出现过度增强。实验结果表明,相比传统的单幅图像除雾方法,所提方法可以有效地恢复图像对比度,并且不会过分强化无雾区域,具有更高的PSNR值和SSIM值。The traditional image defogging method has the problem that the image contrast in the fog-free area is too high,which causes the generated image visual effect is unnatural in some cases.In order to obtain natural and clear defogging images,a new single image defogging method based on weighted near-infrared(NIR)image fusion is proposed.Image contrast is restored by fusing the detail components of NIR images into visible images of the same scene.The NIR image is weighted using the transmission map to prevent excessive enhancement in the fog-free region.The experimental results show that compared with the traditional single image defogging methods,the proposed method can effectively restore the image contrast,does not excessively strengthen the fog-free area,and has higher PSNR and SSIM values.

关 键 词：图像去雾 近红外图像 加权 图像融合 PSNR SSIM 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]