[1]王伟鹏,戴声奎.引导滤波在雾天图像清晰化中的应用[J].华侨大学学报(自然科学版),2015,36(3):263-268.[doi:10.11830/ISSN.1000-5013.2015.03.0263]
　WANG Wei-peng,DAI Sheng-kui.Application of Guided Filter to Haze Image Sharpening[J].Journal of Huaqiao University(Natural Science),2015,36(3):263-268.[doi:10.11830/ISSN.1000-5013.2015.03.0263]
点击复制

引导滤波在雾天图像清晰化中的应用()
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3期
页码:
263-268
栏目:
出版日期:
2015-05-20

文章信息/Info

Title:
Application of Guided Filter to Haze Image Sharpening
文章编号:
1000-5013(2015)03-0263-06
作者:
王伟鹏;  戴声奎
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
College of Information Science and Engineering, Huaqiao University, Xiamen 361021, China
关键词:
雾天图像;  引导滤波;  去雾算法;  大气散射模型;  大气光幕;  图像增强
Keywords:
haze image;  guided filter;  haze removal algorithm;  atmospheric scattering model;  atmospheric veil;  image enhancement
分类号:
TP391.4
DOI:
10.11830/ISSN.1000-5013.2015.03.0263
文献标志码:
A
摘要:
根据大气散射物理模型,分析并解决单幅图像去雾的关键问题,以消除雾气对室外机器视觉系统的影响.实验结果表明:利用引导滤波器的局部平滑特性估计大气光幕,可有效克服光晕效应和颜色过饱和现象;通过计算雾气最浓区域的平均值获取大气光强度值,可解决部分图像偏色问题;对复原的图像进行自适应增强处理,提高了图像的整体视觉效果.通过与多种典型的图像去雾算法的比较,说明该方法能更有效地消除图像中的雾气、真实复原场景的对比度和颜色,同时具有很快的执行速度,有利于算法的实时实现.
Abstract:
According to the physical model of atmospheric scattering, this paper analyses and addresses major problems for single image haze removal to eliminate the effects of fog or haze for outdoor machine vision system. The experimental results show that the proposed method overcomes the limits of halo artifacts and over-saturation through estimating the atmospheric veil using the local smoothing characteristics of guided filter. By computing the average values of the most dense haze to obtain the global atmospheric light intensity, this algorithm could adjust the color cast of the image. Finally, a post-processing procedure is adopted to enhance the visual effect of the recovered image. As compared with typical haze removal algorithms, the proposed method achieves good restoration for contrast and color fidelity more effectively and allows a very fast implementation to achieve real-time.

参考文献/References:

[1] TAN R T.Visibility in bad weather from a single image[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Anchorage:IEEE Press,2008:1-8.
[2] FATTAL R.Single image dehazing[J].ACM Transactions on Graphics,2008,27(3):1-9.
[3] HE Kai-ming,SUN Jian,TANG Xiao-ou.Single image haze removal using dark channel prior[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Miami:IEEE Press,2009:1956-1963.
[4] HE Kai-ming,SUN Jian,TANG Xiao-ou.Guided image filtering[C]//Proceedings of the European Conference on Computer Vision.Heraklion:Springer,2010:1-14.
[5] NARASIMHAN S G,NAYAR S K.Removing weather effects from monochrome images[C]//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Washington D C:IEEE Press,2001:186-193.
[6] 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.
[7] TAREL J P,HAUTIERE N.Fast visibility restoration from a single color or gray level image[C]//Proceedings of the IEEE 12th International Conference on Computer Vision.Kyoto:IEEE Press,2009:2201-2208.
[8] 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.
[9] 王守觉,丁兴号,廖英豪,等.一种新的仿生彩色图像增强方法[J].电子学报,2008,36(10):1970-1973.
[10] HAUTIERE N,TAREL J P,AUBERT D,et al.Blind contrast enhancement assessment by gradient ratioing at visible edges[J].Image Analysis and Stereology,2008,27(2):87-95.

相似文献/References:

[1]贾存坤,戴声奎,卫志敏.采用亮通道先验的低照度图像增强算法[J].华侨大学学报(自然科学版),2018,39(4):595.[doi:10.11830/ISSN.1000-5013.201605078]
　JIA Cunkun,DAI Shengkui,WEI Zhimin.Low Light Image Enhancement Algorithm Using Bright Channel Prior[J].Journal of Huaqiao University(Natural Science),2018,39(3):595.[doi:10.11830/ISSN.1000-5013.201605078]
[2]王伟鹏,戴声奎.引导滤波在雾天图像清晰化中的应用[J].华侨大学学报(自然科学版),2015,36(预先出版):0.
　Wang Wei-peng,Dai Sheng-kui.Application of Guided Filter to Haze Image Sharpening[J].Journal of Huaqiao University(Natural Science),2015,36(3):0.

备注/Memo

备注/Memo:
收稿日期: 2013-12-10
通信作者: 戴声奎(1971-),男,副教授,博士,主要从事图像处理、视频分析和模式识别的研究.E-mail:d.s.k@hqu.edu.cn.
基金项目: 福建省科技计划重点基金资助项目(2013H0030); 中央高校基本科研业务费, 国家自然科学基金培育计划专项基金资助项目(JB-ZR1145)
更新日期/Last Update: 2015-05-20