基于双边滤波的去雾算法

中图法分类号：TP391.41 文献标识码：A 文章编号：1006-8961(2013) - -

论文引用格式：

基于双边滤波的图像去雾

王一帆1 ，尹传历2，黄义明1 ， 王洪玉1

1. 大连理工大学信息与通信工程学院, 辽宁，大连 116024

2. 中国科学院长春光学精密机械与物理研究所, 吉林，长春 130033

摘 要：目的：在雾、霾等天气下，获取的图像受到大气粒子散射的影响而严重降质。针对这一问题，本文提出了一种基于双边滤波的单幅图像去雾算法。方法：此算法是以大气散射模型为基础。首先利用双边滤波保持边缘的平滑特性得到准确的大气耗散函数。其次，针对明亮区域失真的问题，本文提出了弱化明亮区域去雾的方法。最后，通过变换大气散射模型得到清晰的无雾图像。结果：大量实验表明，本算法恢复的图像清晰自然，尤其是在远景处和景深突变的边缘处的处理能取到很好的去雾效果。此外，其时间复杂度为图像大小的线性函数。结论：针对雾、霾天气下的降质图像，基于大气散射模型与双边滤波特性，本文提出了一种新的单幅图像去雾算法。实验表明，本算法能获得很好的去雾效果，尤其在细节处理的表现优于Tarel的去雾算法。同时，与He Kaiming的去雾算法相比，运行时间具有明显优势，有利于实现实时性技术应用。

关键词 ：图像增强；图像去雾；双边滤波；大气散射模型

Image haze removal using bilateral filter

Wang Yifan1，Yin Chuanli2，Huang Yiming 1, Wang Hongyu 1

1. College of Electronic Science and Technology, Dalian University of Technology, Dalian, 116024; 2.Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun, 130033

Abstract: Objective: Images captured in foggy weather are often degraded due to atmospheric particles scatter. Concerning this issue, this paper presents a new haze removal method from single image based on bilateral filter. Method: This algorithm is based on the atmosphere scattering model. First the accurate atmospheric veil is obtained by taking full use of the properties that bilateral filtering is available to preserve edges smooth. Then concerning the distortion of bright portion, a weakening defogging strength method is proposed. Finally the haze-free image is recovered by transforming the atmosphere scattering model. Result: Many experiments show that images restored by this algorithm are clear and natural, especially at the portion for distant scene and where depth changes abruptly. In addition, the time complexity is only a linear function of the input image pixels. Conclusion: Concerning degraded images captured in the fog or haze weather, a new haze removal method from single image is proposed based on the atmosphere scattering model and the bilateral filter. Experiments show