刘雪峰,刘学远,付民

• 1:青岛科技大学自动化与电子工程学院
• 2:中国海洋大学信息科学与工程学院

摘要(Abstract)：

雾霭等天气下获得的图像存在对比度低、颜色退化、景物模糊等一系列图像退化的问题,直接影响了对图像信息的有效利用。因此,对雾天图像进行有效的去雾处理,有效改善降质图像的质量,具有一定的实际意义。分析讨论基于图像增强的多尺度Retinex算法和利用图像复原原理的基于暗原色先验理论的去雾算法,并对具有不同特点的单幅有雾图像进行去雾仿真。实验结果表明,不同理论基础的两种去雾算法各有特点,基于暗原色理论处理得到的图像去雾效果更显著,算法运行速度更快。

关键词(KeyWords)： 图像去雾;图像退化;图像增强;Retinex理论;多尺度Retinex算法;暗原色先验理论

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金资助项目(61401244);; 山东省自然科学基金资助项目(ZR2014FM013;ZR2015FL008);; 山东省高等学校科技计划项目资助项目(J15LN39)~~

作者(Author): 刘雪峰,刘学远,付民

DOI: 10.16652/j.issn.1004-373x.2018.06.005

参考文献(References)：

• [1]涂雅瑗.雾天降质图像的对比度增强方法研究[D].大连:大连海事大学,2009.TU Yayuan.Research on contrast enhancement methods for fogdegraded images[D].Dalian:Dalian Maritime University,2009.
• [2]孙茂金.基于暗通道优先的单幅图像去雾算法研究[D].大连:大连海事大学,2010.SUN Maojin.Research on single image defogging algorithm based on dark channel prior principle[D].Dalian:Dalian Maritime University,2010.
• [3]嵇晓强.图像快速去雾与清晰度恢复技术研究[D].长春:中国科学院研究生院,2012.JI Xiaoqiang.Research on fast image defogging and visibility restoration[D].Changchun:Graduate University of Chinese Academy of Sciences,2012.
• [4]翟艺书.雾天降质图像的清晰化技术研究[D].大连:大连海事大学,2008.ZHAI Yishu.Research of fog-degraded image clearness techniques[D].Dalian:Dalian Maritime University,2008.
• [5]HE K,SUN J,TANG X.Single image haze removal using dark channel prior[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Miami:IEEE,2009:1956-1963.
• [6]DENG L,LI O X,ZHAO S W.An improved image defogging algorithm based on global dark channel prior and fuzzy logic control[C]//Proceedings of 12th International Computer Conference on Wavelet Active Media Technology and Information Processing.Chengdu:IEEE,2015:188-191.
• [7]李坤,兰时勇,张建伟,等.改进的基于暗原色先验的图像去雾算法[J].电路与系统学报,2011,16(2):7-12.LI Kun,LAN Shiyong,ZHANG Jianwei,et al.Improved algorithm on image haze removal using dark channel prior[J].Journal of circuits and systems,2011,16(2):7-12.
• [8]TAREL J P,HAUTIèRE N.Fast visibility restoration from a single color or gray level image[C]//Proceedings of IEEE 12th International Conference on Computer Vision.Kyoto:IEEE,2009:20-28.
• [9]XIE B,GUO F,CAI Z.Improved single image dehazing using dark channel prior and multi-scale retinex[J].Journal of computer research&development,2011,26(5):1070-1079.
• [10]肖燕峰.基于Retinex理论的图像增强恢复算法研究[D].上海:上海交通大学,2007.XIAO Yanfeng.Image enhancement and restoration algorithm based on retinex[D].Shanghai:Shanhai Jiao Tong University,2007.
• [11]赵晓霞,王汝琳,李雪艳.基于多尺度Retinex的雾天降质图像增强算法[J].工矿自动化,2009,35(10):62-64.ZHAO Xiaoxia,WANG Rulin,LI Xueyan.Enhancement algorithm of fog-degraded image based on multiscale retinex[J].Industry and mine automation,2009,35(10):62-64.
• [12]OAKLEY J P,SATHERLEY B L.Improving image quality in poor visibility conditions using a physical model for contrast degradation[J].IEEE transactions on image processing,1998,7(2):167-179.
• [13]LAND E H.Recent advances in retinex theory and some implications for cortical computations:color vision and the natural image[J].Proceedings of the national academy of sciences of the United States of America,1983,80(16):5163-5169.