[1]王伟鹏,戴声奎,项文杰.一种雾天退化场景快速复原方法[J].华侨大学学报(自然科学版),2015,36(2):156-160.[doi:10.11830/ISSN.1000-5013.2015.02.0156]
　WANG Wei-peng,DAI Sheng-kui,XIANG Wen-jie.A Fast Method for Haze Image Restoration[J].Journal of Huaqiao University(Natural Science),2015,36(2):156-160.[doi:10.11830/ISSN.1000-5013.2015.02.0156]
点击复制

一种雾天退化场景快速复原方法()
分享到：

《华侨大学学报（自然科学版）》[ISSN:1000-5013/CN:35-1079/N]

卷:
第36卷
期数:
2015年第2期
页码:
156-160
栏目:
出版日期:
2015-03-20

文章信息/Info

Title:
A Fast Method for Haze Image Restoration
文章编号:
1000-5013(2015)02-0156-05
作者:
王伟鹏;  戴声奎;  项文杰
华侨大学 信息科学与工程学院, 福建 厦门 361021
Author(s):
WANG Wei-peng;  DAI Sheng-kui;  XIANG Wen-jie
College of Information Science and Engineering, Huaqiao University, Xiamen 361021, China
关键词:
去雾;  图像复原;  大气散射模型;  双边滤波;  图像增强
Keywords:
haze removal;  image restoration;  atmospheric scattering model;  bilateral filter;  image enhancement
分类号:
TP391.4
DOI:
10.11830/ISSN.1000-5013.2015.02.0156
文献标志码:
A
摘要:
针对雾天条件下图像退化的问题,提出一种新的场景复原方法.首先,结合大气散射模型与光学反射成像的特性,对大气耗散函数提出物理约束条件,利用双边滤波的边缘保持特性得到大气耗散函数的初始估计.然后,引入局部均值与局部标准差近似估计图像对比度,从而降低对比度较强的部分区域的雾浓度估计来获取更加准确的大气耗散函数.最后,求解雾图成像方程,恢复理想光照条件下的辐射强度.实验结果表明:该方法对图像的细节和颜色恢复非常有效,并能有效克服边缘残雾现象以及颜色过饱和等不足.
Abstract:
According to the problem of image degraded in hazy condition, a new haze image restoration method is proposed. Based on the physical property of atmospheric scattering model and optical reflectance imaging, the physical constraint of atmospheric veil is presented at first. The rough atmospheric veil is obtained by using bilateral filter which has good abilities of keeping edge. Then the local mean and local standard deviation are introduced to estimate the contrast of image, therefore the estimation of local haze density is decreased through good contrast region in order to get more accurate atmospheric veil. Finally, the ideal scene radiance is recovered through solving the equation of haze image. Experimental results show that this method not only achieve great restoration for image detail and color information, but also avoid the shortcomings of edge effect and over saturated.

参考文献/References:

[1] FATTAL R.Single image dehazing[J].ACM Transactions on Graphics,2008,27(3):1-9.
[2] HE Kai-ming,SUN Jian,TANG Xiao-ou.Single image haze removal using dark channel prior[C]//IEEE Conference on Computer Vision and Pattern Recognition.Miami:IEEE Press,2009:1956-1963.
[3] TAREL J,HAUTIERE N.Fast visibility restoration from a single color or gray level image[C]//IEEE 12th International Conference on Computer Vision.Kyoto:IEEE Press,2009:2201-2208.
[4] 禹晶,李大鹏,廖庆敏.基于物理模型的快速单幅图像去雾方法[J].自动化学报,2011,37(2):143-149.
[5] 孙抗,汪渤,周志强,等.基于双边滤波的实时图像去雾技术研究[J].北京理工大学学报,2011,31(7):810-814.
[6] 张冰冰,戴声奎,孙万源.基于暗原色先验模型的快速去雾算法[J].中国图象图形学报,2013,18(2):184-188.
[7] 甘佳佳,肖春霞.结合精确大气散射图计算的图像快速去雾[J].中国图象图形学报,2013,18(5):583-590.
[8] NARASIMHAN S G,NAYAR S K.Removing weather effects from monochrome images[C]//IEEE Conference on Computer Vision and Pattern Recognition.Washington DC:IEEE Press,2001:186-193.
[9] NARASIMHAN S G,NAYAR S K.Contrast restoration of weather degraded images[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(6):713-724.
[10] TOMASI C,MANDUCHI R.Bilateral filtering for gray and color images[C]//Proceedings of IEEE international Conference on Computer Vision.Bombay:IEEE Press,1998:839-846.
[11] CHEN J W,PARIS S,DURAND F.Real-time edge-aware image processing with the bilateral grid[J].ACM Transactions on Graphics,2007,26(3):103-111.
[12] PARIS S,DURAND F.A fast approximation of the bilateral filter using a signal processing approach[J].International Journal of Computer Vision,2009,81(1):24-52.

备注/Memo

备注/Memo:
收稿日期: 2014-01-20
通信作者: 戴声奎(1971-),男,副教授,博士,主要从事计算机视觉和图像复原的研究.E-mail:d.s.k@hqu.edu.cn.
基金项目: 福建省科技计划重点项目(2013H0030); 中央高校基本科研业务费专项基金资助项目(JB-ZR1145)
更新日期/Last Update: 2015-03-20