基于Wiener滤波的快速视频去雾算法

雾霾环境会极大的降低视频中事物的能见度。针对于目前去雾算法存在运算复杂度大、处理时间长的缺点，提出一种基于Wiener滤波的快速去雾算法，首先获取暗原色模型，通过Wiener滤波自适应获取透射率分布图并进行初级及深度去雾，最后通过自适应对数变换进行亮度调整，得到去雾后图像。实验证明，相比现有的先进方法，本文的算法具有处理速度快和去雾效果好的优点。

A Fast Wiener-filter based Dehazing Method for Vision

The visibility of video will be greatly reduced by haze. The common disadvantages of existing dehazing algorithms are high computational-complexity and long processing time. A fast Wiener-filter based dehazing method is proposed to solve the problem. The model of dark channel is obtained first. Wiener-filter is designed for adaptively computing out the transmittance distribution maps, which are implemented for preliminary and advanced dehazing. The result image is obtained by the brightness adjustment of adaptive logarithmic transformation. The experimental results demonstrate that the performance of the proposed method is more fast and efficient than that of state-of-the-art.