基于多光源模型的夜晚雾天图像去雾算法

依据夜间多光源导致强光处能见度低的现象，在传统大气散射模型中定义发光因子项，构建了一个专门针对夜晚雾天图像的去雾模型，在此基础上提出了一种夜晚雾天图像去雾算法.该算法将原输入图像分解为新雾天图像层和发光图像层，然后对此分解得到的新雾天图像层进行色偏纠正和引导滤波操作以得到最终的去雾结果.与暗原色原理方法、快速中值滤波方法、图像颜色迁移方法、夜晚成像模型方法等已有方法的对比实验证实了本文算法的有效性.该算法可应用于汽车防碰撞系统、道路监控系统，以及其他识别系统.

Nighttime Image Defogging Based on Multiple Light Source Model

Multiple light sources cause the low visibility in the brightest region in nighttime images,a glow term was defined in the traditional atmospheric scattering model.A defogging model was constructed for nighttime foggy images.Based on the model,a nighttime image defogging algorithm was proposed.The algorithm decomposed the original image into a nighttime foggy image layer and a glow image layer,and then the color-shift correction operation and the guided filter were applied for the foggy image layer.Thus,the defogging results can be obtained.Comparisons with dark channel prior method,fast median filter method,image color transfer method,and nighttime imaging model method verified the effectiveness of the proposed algorithm.This algorithm can be applied in such devices as vehicle collision avoidance systems,traffic surveillance systems,and other recognition systems.