海雾下的视频图像去雾算法研究  

Video image defogging algorithm research under sea fog

作　　者：马忠丽[1] 文杰[1] 梁秀梅[1] 

机构地区：[1]哈尔滨工程大学自动化学院,哈尔滨150001

出　　处：《计算机应用研究》2014年第9期2836-2840,共5页Application Research of Computers

基　　金：国家自然科学基金青年基金资助项目(51109047);国家留学基金委留学基金资助项目(2011307358)

摘　　要：针对海雾下大气粒子的散射作用使得水面舰船视觉系统的视频图像严重降质问题,采用基于大气散射物理模型的海雾去雾方法。针对海上图像海天交界线明显、天空区域较大的特点,对图像进行分割,分析天空区域特征得到天空亮度估计值,通过求解大气散射物理模型实现对图像的清晰化处理;并且利用帧差法背景提取方法,通过计算同一背景下雾的分布图提高视频图像的去雾速率。与现有的几种效果较好的陆上去雾方法进行对比研究,结果表明该方法能够在多变的海雾下增强视频图像的清晰度。Under the sea fog, atmospheric particles scattering leads to serious video image degradation of the surface ships vis- ual system. This paper used the method of atmospheric scattering physical model to remove the sea fog, due to obvious sea-sky- line and the larger sky area .characteristics. Firstly, the methoddid the image segmentation, and estimated the sky brightness through analyzing sky area characteristics. And then it solved atmospheric scattering physical model and finished image scene recovery. It could obtain the background by using the method of frame difference background extraction, and then calculated the fog distribution image under the same background, which increased the defogging rate of video image. Comparative re- search with several defogging methods onshore, results show that the proposed method can enhance the video image clarity un- der the changeable sea fog.

关 键 词：海雾 物理模型 海天线 去雾 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TP301.6[自动化与计算机技术—计算机科学与技术]