计算机应用 ›› 2011, Vol. 31 ›› Issue (05): 1224-1226.DOI: 10.3724/SP.J.1087.2011.01224

• 图形图像技术 • 上一篇    下一篇

基于邻域相似性的暗原色先验图像去雾方法

郭珈1,王孝通1,2,胡程鹏1,徐晓刚3   

  1. 1.海军大连舰艇学院 光电技术研究所,辽宁 大连 116018
    2.海军大连舰艇学院 航海系,辽宁 大连 116018
    3.海军大连舰艇学院 自动化系,辽宁 大连 11018
  • 收稿日期:2010-11-09 修回日期:2011-01-02 发布日期:2011-05-01 出版日期:2011-05-01
  • 通讯作者: 郭珈
  • 作者简介:郭珈(1983-),女,辽宁大连人,博士研究生,主要研究方向:图像处理、信号分析;王孝通(1962-),男,浙江义乌人,教授,博士,主要研究方向:电子海图、图像处理;胡程鹏(1983-),男,山东济宁人,硕士研究生,主要研究方向:交通信息处理、图像处理;徐晓刚(1967-),男,浙江永康人,教授,博士,主要研究方向:信号分析、虚拟仿真。
  • 基金资助:

    国家自然科学基金资助项目(60975016);国家青年科学基金资助项目(61002052);辽宁省自然科学基金资助项目(20082176)。

Image dehazing method based on neighborhood similarity dark channel prior

GUO Jia1, WANG Xiao-tong1,2, HU Cheng-peng1, XU Xiao-gang3   

  1. 1. Institute of Photoelectric Technology, Dalian Naval Academy, Dalian Liaoning 116018, China
    2. Department of Navigation, Dalian Naval Academy, Dalian Liaoning 116018, China
    3. Department of Equipment Automatization, Dalian Naval Academy, Dalian Liaoning 116018, China
  • Received:2010-11-09 Revised:2011-01-02 Online:2011-05-01 Published:2011-05-01
  • Contact: GUO Jia

摘要: 针对雾天图像对比度和颜色严重退化的问题,提出了一种应用暗原色先验去雾的简便方法。该方法首先根据暗原色先验得到雾天透射率图;然后,通过暗原色值与邻域暗色值的差值来判断边缘,取颜色最相近点的暗色值为新的暗原色值,同时利用暗原色图像直方图自动获得大气光线值;最后,根据大气散射模型得到清晰图像。实验证明,该方法能够有效去除雾对图像的影响。

关键词: 去雾, 物理模型, 暗原色先验, 透射率, 邻域相似性

Abstract: Images acquired in bad weather have poor contrasts and colors. This paper proposed a simple method to remove haze based on dark channel priority. After acquiring the transmission, getting the difference between the dark channel and dark value of nearest eight pixels, the pixel of minimal difference was redefined as new dark channel. Besides, the air light was automatically estimated from the histogram of the dark channel. At last, the clear image could be recovered based on physical model. The experimental results show that the method can sharp the edge and improve the quality of the degraded image.

Key words: dehazing, physical model, dark channel prior, transmission, neighborhood similarity