单幅图像的快速去雾算法  

Fast dehazing algorithm for a single image

作　　者：黄黎红[1] 

机构地区：[1]莆田学院电子信息工程系,福建莆田351100

出　　处：《光电子．激光》2011年第11期1735-1738,1744,共5页Journal of Optoelectronics·Laser

基　　金：福建省教育厅科技研究项目(JB10142)

摘　　要：雾的存在使得户外图像的处理变得困难。雾、霭、烟等现象会使彩色图像退化,对比度降低。介绍了一种单幅图像的去雾新算法,不需要分割图像,直接利用高斯低通滤波器分离出背景空气光,利用改良的暗通道法对大气光进行估计,结合雾天图像的物理模型对图像进行复原,最后再对图像的饱和度进行校正,得到最终的复原效果。该算法的主要优点是速度快,且不仅可以应用于彩色图像,也可以适用于灰度图像。最后通过几种算法的实验结果比较和分析,表明本文算法是有效的。Processing outdoor images is difficult with the presence of haze, fog or smoke which fades the colors and reduces the contrast of the observed objects. A novel algorithm for a single image dehazing is proposed in this paper. It doesn＇t need to segment the image. The background airlight is separated directly by Gauss low-pass filter. The atmospheric light is estimated by the refinement dark channel prior. Combined with the physical model of haze image,the image is restored, the saturation is calibrated, and then the final effect of restoration is obtained. The main advantage of the proposed algorithm is the speed. Another advantage is the possibility to handle both color images and gray level images. The experimental results of the proposed algorithm and other algorithms are compared and analyzed to illustrate the effectiveness of the proposed method.

关 键 词：单幅图像去雾 物理模型 图像复原 图像分割 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]