计算机应用 ›› 2014, Vol. 34 ›› Issue (3): 820-823.DOI: 10.11772/j.issn.1001-9081.2014.03.0820

• 虚拟现实与数字媒体 • 上一篇    下一篇

基于曝光融合的单幅图像去雾算法

唐鉴波1,朱桂斌1,王田2,郭雨1,江铁3   

  1. 1. 重庆通信学院 应急通信重庆市重点实验室,重庆400035
    2. 重庆富伦麦柯信息技术有限公司,重庆400035;
    3. 61655部队,重庆402764
  • 收稿日期:2013-08-22 修回日期:2013-10-24 出版日期:2014-03-01 发布日期:2014-04-01
  • 通讯作者: 唐鉴波
  • 作者简介:唐鉴波(1989-),男,四川南充人,硕士研究生,主要研究方向:图像处理、计算机视觉;朱桂斌(1972-),男,河北涿鹿人,教授,博士,主要研究方向:信息隐藏、模式识别;王田(1971-),男,湖北荆州人,副教授,博士,主要研究方向:移动智能网、多媒体通信。
  • 基金资助:

    国家自然科学基金资助项目;应急通信重庆市重点实验室开放课题项目

Single image dehazing method based on exposure fusion

TANG Jianbo1,ZHU Guibin1,WANG Tian2,GUO Yu1,JIANG Tie3   

  1. 1. Chongqing Key Laboratory of Emergency Communication, Chongqing Communication Institute, Chongqing 400035, China;
    2. Chongqing Fulun-Magcard Information Technology Company Limited, Chongqing 400035, China;
    3. No.61655 Troops, Chongqing 402764, China
  • Received:2013-08-22 Revised:2013-10-24 Online:2014-03-01 Published:2014-04-01
  • Contact: TANG Jianbo
  • Supported by:

    National Natural Science Foundation

摘要:

针对雾霾等恶劣天气导致户外图像降质的问题,设计了一种简单、高效的图像去雾算法。首先通过空域高通滤波对降质图像进行处理,达到压制低频分量、增强图像边缘细节的目的;然后,对滤波后的图像进行空间线性对比度拉伸,增强图像的对比度;最后通过拉普拉斯金字塔的多曝光图像融合方法,将滤波结果与对比度拉伸结果进行融合,得到最终的去雾图像。实验结果表明,所提算法实时性较高,对雾霾、沙尘、水下等降质图像均有较好的增强效果。

关键词: 图像处理, 图像去雾, 空域高通滤波, 曝光融合

Abstract:

Outdoor images captured in bad weather often have poor qualities in terms of visibility and contrast. A simple and effective algorithm was designed to remove haze. Firstly, the spatial high-pass filtering was used to suppress the low-frequency component and enhance the edge detail, and then the contrast-stretching transformation was used to acquire an image with high dynamic range. Finally, the exposure fusion method based on Laplacian pyramid was utilized to fuse the two results above and get the defogged image. The experimental results show that the proposed method has a good performance on enhancing images that are degraded by fog, dust or underwater and it is appropriate for real-time applications.

Key words: image processing, dehazing, spatial-domain high pass filter, exposure fusion

中图分类号: