一种基于分割的图像去雾新算法
基金项目:

国家自然科学基金资助项目(61071161)



A new segmentation based image defogging algorithm
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
    摘要:

    在雾天环境下,大气介质中悬浮颗粒的散射作用导致图像质量严重下降,限制了其使用范围,因此对雾天图像进行去雾处理是必要的。根据暗原色先验去雾的原理,在局部区域内基于图像分割的思想来较准确快速估计雾天图像的传播图,然后应用大气散射模型对雾天图像进行去雾处理,并通过直方图拉伸来增大处理后的图像的对比度。实验结果表明,该算法能有效去除雾气对图像的影响,与传统去雾算法相比较,具有较快的处理速度和较强的实用性。

    Abstract:

    It is very necessary to defog the images captured in the foggy days,because the scattering effect of atmospheric suspending particles will lead to serious image degradation,which directly influences the visual effect and its application range. Based on the principle of dark channel priority,a segmentation model is introduced to estimate a image transmission map precisely and fast in local area, and then the atmosphere scattering model is applied to defog the images,and the image contrast after defogging is enhanced by histogram stretching. Experiment results show that the proposed algorithm efficiently removes the influence of the fog to the image with high processing speed and wide application range.

    参考文献
    相似文献
    引证文献
引用本文

桓宗圣,陶青川,田 旺.一种基于分割的图像去雾新算法[J].太赫兹科学与电子信息学报,2013,11(2):254~259

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
历史
  • 收稿日期:2012-12-04
  • 最后修改日期:2013-01-04
关闭