基于雾浓度的去雾方法
Image Haze Removal Based on Haze Density
DOI: 10.12677/CSA.2018.812201, PDF,    国家自然科学基金支持
作者: 乔美丽*：山东省教育招生考试院，山东 济南；王 平, 杜宏伟, 刘新新：山东财经大学计算机科学与技术学院，山东 济南;山东省数字媒体技术重点实验室，山东 济南
关键词: 雾天图像退化模型；暗原色先验；雾浓度；滤波平滑；局部大气光；Haze Image Degradation Model； Dark Channel Prior； Haze Density； Filtering Smoothing； Local Atmospheric Light
摘要: 图像去雾是计算机视觉的重要研究方向，去雾的同时保证图像亮度合适，色彩不失真，不造成信息丢失是图像去雾需解决的问题，为此提出了一种基于雾浓度的去雾方法。首先，根据雾浓度的差异将有雾图像划分为浓雾、雾和薄雾区域。其次，对于不同雾浓度区域，利用暗原色先验知识估计局部大气光值。然后，利用局部大气光值进一步估计透射率。最后，根据雾图降质模型，利用局部大气光值和透射率恢复出无雾图像。实验结果表明，本方法简单易行，能够得到更优的视觉效果以及客观数据。
Abstract: Image haze removing plays a significant role in computer vision. The goal of dehazing is to remove haze completely, with appropriate brightness, rich details and real color. Then, a dehazing method based on haze density is proposed. Firstly, according to the difference of haze density, the hazy image is divided into three regions: dense fog region, fog region, and light fog region. Secondly, for different regions, the local atmospheric light is estimated based on the dark channel prior. Then, the transmission map is estimated by using the local atmospheric light. Finally, on the basis of the degradation model, the haze-free image is restored through local atmospheric light and transmission map. Experimental results demonstrate that the proposed method is simple and easy, with high visual effects and objective data.
文章引用：乔美丽, 王平, 杜宏伟, 刘新新. 基于雾浓度的去雾方法[J]. 计算机科学与应用, 2018, 8(12): 1813-1822. https://doi.org/10.12677/CSA.2018.812201

参考文献

[1] 张久鹏, 张伟. 基于反转的限制对比度自适应直方图均衡图像去雾改进算法[J]. 物联网技术, 2015, 5(2): 10-12.
[2] 张赛楠, 吴亚东, 张红英, 王松. 改进的单尺度Retinex雾天图像增强算法[J]. 激光与红外, 2013, 43(6): 698-7028.
[3] Wang, M., Zhou, S.D., Huang, F. and Liu, Z.H. (2011) The Study of Color Image Defogging Based on Wavelet Transform and Single Scale Retinex. Proceedings of SPIE—The International Society for Optical Engineering, Bellingham, WA, June 2011, 81940F. [Google Scholar] [CrossRef] 
[4] Narasimhan, S.G. and Nayar, S.K. (2000) Chromatic Framework for Vision in Bad Weather. IEEE Conference on Computer Vision and Pattern Reorganization, Hilton Head Island, 15 June 2000, 598-605. [Google Scholar] [CrossRef] 
[5] Narasimhan, S.G. and Nayar, S.K. (2003) Contrast Restoration of Weather Degraded Images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 25, 713-724. [Google Scholar] [CrossRef] 
[6] Nayar, S.K. and Narasimhan, S.G. (1999) Vision in Bad Weather. IEEE In-ternational Conference on Computer Vision, 2, 820-827. [Google Scholar] [CrossRef] 
[7] Schechner, Y.Y., Narasimhan, S.G. and Nayar, S.K. (2001) Instant Dehazing of Images Using Polarization. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1, I-325−I-332. [Google Scholar] [CrossRef] 
[8] Shwartz, S., Namer, E. and Schechner, Y.Y. (2006) Blind Haze Separation. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2, 1984-1991. [Google Scholar] [CrossRef] 
[9] Schechner, Y.Y. and Averbuch, Y. (2007) Regularized Image Recovery in Scattering Media. IEEE Transactions on Pattern Analysis and Machine Intelligence, 29, 1655-1660. [Google Scholar] [CrossRef] 
[10] Fattal, R. (2008) Single Image Dehazing. Proceedings of the ACM Transactions on Graphics, 27, Article No.72. [Google Scholar] [CrossRef] 
[11] Meng, G.F., Wang, Y., Duan, J.Y., Xiang, S.M. and Pan, C.H. (2013) Efficient Image Dehazing with Boundary Constraint and Contextual Regularization. IEEE International Conference on Computer Vision, 1-8 December 2013, 617-624.
[12] He, K.M., Sun, J. and Tang, X.O. (2011) Single Image Haze Removal Using Dark Channel Prior. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33, 2341-2353. [Google Scholar] [CrossRef] 
[13] Fang, F., Li, F., Yang, X.M., Shen, C.M. and Zhang, G.X. (2010) Single Image Dehazing and Denoising with Variational Method. Proceedings of the International Conference on Image Analysis and Signal Pro-cessing, Zhejiang, 9-11 April 2010, 219-222.
[14] Gibson, K.B., Võ, D.T. and Nguyen, T.Q. (2012) An Investigation of Dehazing Effects on Image and Video Coding. IEEE Transactions on Image Processing, 21, 662-673. [Google Scholar] [CrossRef] 
[15] Pavlic, M., Belzner, H., Rigoll, G. and Ilic, S. (2012) Image Based Fog Detection in Vehicles. IEEE Intelligent Vehicles Symposium, Alcala de Henares, 3-7 June 2012, 1132-1137. [Google Scholar] [CrossRef] 
[16] Reinhard, E., Stark, M., Shirley, P. and Ferwerda, J. (2002) Photographic Tone Reproduction for Digital Images. Proceedings of the 29th Annual Conference on Computer Graphics and Interactive Techniques, San Antonio, 23-26 July 2002, 267-276. [Google Scholar] [CrossRef] 
[17] Hautuere, N., Tarel, J.P., Aubert, D. and Dumont, E. (2008) Blind Contrast Enhancement Assessment by Gradient Rationing at Visible Edges. Image Analysis and Stereology Journal, 27, 87-95. [Google Scholar] [CrossRef]