基于光照估计的夜间图像去雾

相对白天雾天图像，夜晚雾天图像具有整体亮度低、光照不均匀、偏色等特点，因此去雾难度大。本文从夜间雾天成像规律出发，提出了基于光照估计的夜间图像去雾算法。针对光照不均匀问题，通过估计光照图来去除不均匀光照的影响；针对目前白天去雾算法假设不适用于夜晚图像问题，提出基于信息熵的传输图粗估计的方法；针对颜色失真问题，通过统计光源区域的颜色属性来进行颜色校正。实验结果表明，本文算法能够有效的去除不均匀光照影响，提高图像对比度，改善图像视觉效果。

Nightti me Haze Re moval Based on Illu mination Esti mation

Nighttime haze removal is more difficult,since nighttime hazy images contain degradation more serious than daytime’s due to illumination,resulting in lower brightness,lower contrast,uneven illumination,and chromatic aberra-tion,etc.Depending on imaging law of nighttime hazy image,a novel dehazing algorithm based on illumination estimation is presented.Firstly,the uneven illumination is removed by estimate the illumination map.Secondly,an entropy-based scheme for nighttime images is proposed to obtain transmission map.Finally,the color of illumination is estimated by statistics of source regions.The experimental results show that the proposed algorithm can effectively remove the uneven illumination effect,increase the image contrast and improve the image visual effect.