基于自适应大气光校正的图像去雾方法

针对暗通道先验去雾算法的不足,提出一种自适应大气光校正的改进算法。利用四叉树算法粗略估计大气光,利用提出的自适应大气光校正方法校正粗略估计的大气光;利用均值滤波代替最小值滤波得到暗通道,进而得到平滑的透射率,该透射率不需细化;使用一种自适应透射率补偿方法对天空等明亮区域的透射率进行动态修正;根据大气散射模型复原出无雾图像,并对无雾图像进行色调调整,用来得到清晰明亮的输出图像。实验结果表明,该算法具有较快的处理速度,同时所恢复出的图像细节突出,具有较好的视觉效果。

IMAGE DEHAZING BASED ON ADAPTIVE ATMOSPHERIC LIGHT CORRECTION

To overcome the shortcomings of dark channel prior dehazing algorithm, this paper proposed an improved adaptive atmospheric light correction algorithm. We used quad-tree algorithm to estimate atmospheric light roughly, and the proposed adaptive atmospheric light correction method was adopted to correct the roughly estimated atmospheric light. The mean filter was used instead of minimum filter to get dark channel, and then smooth transmittance was obtained, which need not be refined. We used an adaptive transmittance compensation method to dynamically modify the transmittance of bright areas such as the sky. According to the atmospheric scattering model, the haze-free image was restored, and the color of the haze-free image was adjusted to obtain a clear and bright output image. The experimental results show that the algorithm has faster processing speed, and provide more detailed restored image with good visual effects.