杨爱萍, 赵美琪, 宋曹春洋, 王金斌
AuthorsHTML:杨爱萍, 赵美琪, 宋曹春洋, 王金斌
AuthorsListE:Yang Aiping, Zhao Meiqi, Song Caochunyang, Wang Jinbin
AuthorsHTMLE:Yang Aiping, Zhao Meiqi, Song Caochunyang, Wang Jinbin
Unit:天津大学电气自动化与信息工程学院，天津 300072
Unit_EngLish:School of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China
Abstract_Chinese:针对阴天或夜晚等弱光条件下拍摄的图像具有亮度低、对比度低和细节模糊等问题, 提出了一种基于色调映射和暗通道融合的弱光图像增强方法．首先, 根据弱光及其反转图像的特点, 提出面向弱光图像的透射率估计方法, 进而获得场景深度信息, 并将其融入色调映射函数设计; 同时利用暗通道图像区分光源区域, 以修正色调映射函数参数, 使其能够根据场景深度自适应调整图像亮度; 另一方面, 增强后的暗通道图可有效突出图像的细节信息, 将经过色调映射后的V通道图像和暗通道图进行加权融合, 得到最后的增强结果．实验结果表明, 本文方法不仅显著改善图像亮度、增强对比度、恢复出更多的图像细节, 还能有效去除块效应和晕轮伪影, 视觉效果理想．
Abstract_English:Images captured at night or under low light conditions have the problems of low intensity，low contrast and blurring of details. This paper proposed a new low-light image enhancement method based on tone mapping and dark channel fusion. Firstly，an improved transmission estimation method was presented to obtain the depth information by using the statistics?characteristics of low light image and its inversion. Then，the tone mapping function was designed by incorporating the scene depth. In addition，the pixel-wise dark channel was used to recognize the light source region with the purpose of modifying the parameter of the tone mapping function，and so the image brightness can be adjusted adaptively. In order to preserve more image details，the pixel-wise dark channel was enhanced and fused with the enhanced V-channel image to get the final results. Experimental results show that the proposed method not only improves the image brightness and contrast with more details，but also removes block effects and halo artifacts with ideal visual effects.
Keyword_Chinese:图像增强; 深度信息; 色调映射; 暗通道; 融合
Keywords_English:image enhancement; depth information; tone mapping; dark channel; fusion

PDF全文下载地址:http://xbzrb.tju.edu.cn/#/digest?ArticleID=6060