基于暗通道先验的单幅图像快速去雾方法

为了提高雾天图像的去雾效果,针对暗通道先验法则中存在的不足,提出一种单幅图像快速去雾方法.该方法以暗通道先验法则为基础,采用四叉树搜索算法对大气光值进行估计,并通过白平衡对大气散射模型进行简化.然后,利用暗通道先验知识得到介质传输率粗略估计,并通过引导滤波和双阈值判断方法对介质传输率中边缘和天空区域进行优化.最后,通过简化大气散射模型和色调调整得到去雾图像.与几种典型的图像去雾方法相比,该方法运算速度较快,能有效提高去雾图像的清新度,并获得较好的图像颜色.

Fast Single-image Dehazing Method Based on Dark Channel Prior

In order to improve the dehazing effect of hazed image,a fast single-image dehazing method based on dark channel prior was proposed in allusion to the defect of dark channel prior rule.Based on the dark channel prior rule,the quad-tree search algorithm was adopted to estimate the value of atmospheric optical,which is used to simplify the atmospheric scattering model by the white balance.Then,the coarse estimation of medium transmission was obtained through the dark channel prior knowledge,and the guided filter and double-threshold judgment method were used to optimize the fringe and sky regions.Finally,the simplified atmospheric scattering model and tone mapping were adopted to get the dehazed image.Compared to some state-of-the-art methods,the proposed method can achieve a faster processing speed,effectively improve the definition of the dehazed image,and obtain good image color.