[1]刘子兵,戴声奎.大气光幕融合的去雾新方法[J].华侨大学学报(自然科学版),2018,39(2):246-251.[doi:10.11830/ISSN.1000-5013.201509026]
　LIU Zibing,DAI Shengkui.Novel Haze Removal Method Based on Atmospheric Veil Fusion[J].Journal of Huaqiao University(Natural Science),2018,39(2):246-251.[doi:10.11830/ISSN.1000-5013.201509026]
点击复制

大气光幕融合的去雾新方法()
分享到：

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

卷:
第39卷
期数:
2018年第2期
页码:
246-251
栏目:
出版日期:
2018-03-20

文章信息/Info

Title:
Novel Haze Removal Method Based on Atmospheric Veil Fusion
文章编号:
1000-5013(2018)02-0246-06
作者:
刘子兵;  戴声奎
华侨大学 信息科学与工程学院, 福建 厦门 361021
Author(s):
LIU Zibing;  DAI Shengkui
College of Information Science and Engineering, Huaqiao University, Xiamen 361021, China
关键词:
图像复原;  图像去雾;  大气散射模型;  大气光幕;  图像融合
Keywords:
image restoration;  haze removal;  atmospheric scattering model;  atmospheric veil;  image fusion
分类号:
TP391.41
DOI:
10.11830/ISSN.1000-5013.201509026
文献标志码:
A
摘要:
针对雾天场景成像设备采集的图像存在对比度低、细节不清晰的问题,提出一种结合大气光幕融合的雾天场景复原算法.首先,基于不同场景深处大气光幕的物理特性和光学成像特性,获取远景雾气分布的近似估计.其次,通过像素级融合和滤波的方法得出准确的全局大气光幕.最后,通过反演大气散射模型得到复原图像,并进行亮度和色调调整.该方法可以有效避免过度去雾现象和光晕效应等不足,能快速复原场景的对比度和颜色.实验结果表明:该算法简单高效,具有较强场景适应能力,并保证实时性.
Abstract:
In order to enhance contrast and detail information of haze image captured by the imaging system, a haze scene restoration algorithm based on atmospheric veil fusion is proposed. Firstly, the haze density distribution of distant area is roughly estimated based on the physical properties of the atmospheric veil in different depth and the optical reflectance imaging. Then, the global atmospheric veil is accurately estimated by using image fusion and filtering on the pixel level. Finally, the restored image is obtained through the inversion of the atmospheric scattering model, and the brightness and chroma of the images are adjusted via tone mapping. This method can avoid over defogging or halo artifacts and achieving a satisfactory restoration for better contrast and color fidelity. The experimental results yield that the proposed method is not only very simple and efficient, but also has robust scene adaptability and achieves real-time performance.

参考文献/References:

[1] HE Kaiming,SUN Jian,TANG Xiaoou.Single image haze removal using dark channel prior[C]//IEEE Conference on Computer Vision and Pattern Recognition.Miami:IEEE Press,2009:1956-1963.DOI:10.1109/CVPRW.2009.5206515.
[2] HE Kaiming,SUN Jian,TANG Xiaoou.Guided image filtering[C]//Proceeding of the European Conference on Computer Vision.Heraklion:Springer,2010:1-14.DOI:10.1109/TPAMI.2012.213.
[3] TAREL J P,HAUTIÉRE N.Fast visibility restoration from a single color or gray level image[C]//Proceedings of IEEE 12th International Conference on Computer Vision.Washington D C:IEEE Press,2009:2201-2208.DOI:10.1109/ICCV.2009.5459251.
[4] TAREL J P,HAUTIÉRE N,CORD A,et al.Improved visibility of road scene images under heterogeneous fog[C]//Intelligent Vehicles Symposium(IV).[S.l.]:IEEE Press,2010:478-485.DOI:10.1109/IVS.2010.5548128.
[5] KIM J H,JANG W D,SIM J Y,et al.Optimized contrast enhancement for real-time image and video dehazing[J].Journal of Visual Communication and Image Representation,2013,24(3):410-425.DOI:10.1016/j.jvcir.2013.02.004.
[6] 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.
[7] 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.
[8] NARASIMHAN S G,NAYAR S K.Vision and the atmosphere[J].International Journal of Computer Vision,2002,48(3):233-254.
[9] TTÉVENAZ P,SAGE D,UNSER M.Bi-exponential edge-preserving smoother[J].IEEE Transactions on Image Processing a Publication of the IEEE Signal Processing Society,2012,21(9):3924-3936.
[10] HAUTIÉRE N,TAREL J P,AUBERT D,et al.Blind contrast enhancement assessment by gradient ratioing at visible edges[J].Image Analysis and Stereology Journal,2008,27(2):87-95.

相似文献/References:

[1]刘子兵,戴声奎.结合天空分割修正的快速去雾方法[J].华侨大学学报(自然科学版),2018,39(1):133.[doi:10.11830/ISSN.1000-5013.201508054]
　LIU Zibing,DAI Shengkui.Fast Dehaze Algorithm Based on Sky Region Segmentation and Modification[J].Journal of Huaqiao University(Natural Science),2018,39(2):133.[doi:10.11830/ISSN.1000-5013.201508054]

备注/Memo

备注/Memo:
收稿日期: 2015-09-19
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项目(2013H0030); 中央高校基本科研业务基金资助项目(JB-ZR1145)
更新日期/Last Update: 2018-03-20