摘要
针对暗通道先验去雾不适用于含有大量天空区域的雾化图像的缺陷,提出一种自适应图像去雾算法。基于大气散射模型,利用暗通道图像,分割天空与非天空区域,在天空区域使用颜色衰减先验,非天空区域则使用暗通道先验求解透射率,并改进暗通道先验中全局大气光值的求解,最后使用加权导向滤波去噪。实验结果表明,所提算法在主观和客观评价中均优于所列的其它算法,去雾后的图像避免了天空区域的过饱和现象,减弱了光晕效应,非天空区域更自然,视觉效果更好。针对雾化图像的去雾处理,通过理论推导和实验仿真对比,说明所提算法改进的可行性,并具有一定的优越性,能较好地处理含有天空区域的雾化图像。
Aiming at the defect that the dark channel prior dehazing is not suitable for fogged images containing a large number of sky regions, an adaptive image defogging algorithm is proposed. Based on the atmospheric scattering model, the dark channel image is used to separate the sky and non-sky areas. To solve the transmittance, the color attenuation prior is used in the sky area, while the dark channel prior is used in the non-sky area, and the global atmospheric light in dark channel prior is improved. The solution is finally denoised using weighted guided filtering. Experimental results show that the proposed algorithm is superior to other listed algorithms in both subjective and objective evaluation. The dehazed image avoids oversaturation in the sky area, reduces the halo effect, and makes non-sky areas more natural and visual effects better. Aiming at the defogging processing of the fogged image, through theoretical derivation and experimental simulation comparison, the feasibility of the improvement of the proposed algorithm is demonstrated, and it has certain advantages and can better process the fogged image containing the sky area.
作者
孙希延
陶堃
黄建华
时慧恩
SUN Xi-yan;TAO Kun;HUANG Jian-hua;SHI Hui-en(Guanxi Key Laboratory of Precision Navigation Technology and Application,Guilin University of Electronic Technology,Guilin Guangxi 541004,China;National&Local Joint Engineering Research Center of Satellite Navigation and Location Service,Guilin University of Electronic Technology,Guilin Guangxi 541004,China)
出处
《计算机仿真》
北大核心
2022年第6期359-364,共6页
Computer Simulation
基金
国家自然科学基金(61561016,61861008,11603041)
2019年桂林市科技计划项目重大专项计划(20190219-1)
桂林电子科技大学研究生教育创新计划项目(2020YCXS026)。
关键词
暗通道
图像去雾
天空分割
导向滤波
Dark channel
Image dehazing
Sky segmentation
Guided filter
作者简介
孙希延(1973-),女(汉族),山东潍坊市人,博士,研究员,主要研究领域为卫星导航与数字信号处理;陶堃(1993-),男(汉族),广西贺州市人,硕士研究生,主要研究领域为无人机图像处理;通讯作者:黄建华(1964-),男(汉族),湖南永州市人,教授,硕士研究生导师,主要研究领域为卫星导航、卫星及无人机遥感;时慧恩(1995-),女(汉族),辽宁丹东市人,硕士研究生,主要研究方向为遥感影像处理。
