基于补偿暗通道和透射率融合的图像去雾算法

针对暗通道先验算法去雾不彻底且透射率估计不准确的问题,提出了一种基于补偿暗通道和透射率融合的去雾算法。该方法首先用中值滤波补偿暗通道,解决复原图像边缘细节不突出问题;然后由补偿暗通道得到透射率的简单估计及白平衡得到透射率的模糊估计,将两者进行像素级融合,得到透射率的精确估计;最后根据大气散射模型恢复出无雾图像。实验结果表明,该算法获得了较为精确的透射率,复原图像有效消除了残雾和Halo现象,在天空区域有较好的色彩保真度,同时也有效提升了运算速度。

Image Haze Removal Algorithm Based on Compensation of Dark Channel and Transmission Fusion

Aiming at the problem of not eliminating the fog thoroughly and estimating transmission inaccurately of dark channel priori algorithm, the haze removal algorithm based on the compensating dark channel and transmission fusion is proposed. In this method, the median filter is used to compensate the dark channel to solve the problem that the edge details of the restored image are not conspicuous. Then, the simple and fuzzy estimation of transmission are obtained by compensating for the dark channel and white balance respectively, and they are merged at the pixel-level to obtain accurate estimation of the transmission.Finally, the haze-free image is recovered according to the atmospheric scattering model. The experimental results show that the proposed algorithm achieves a more accurate transmission rate. The reconstructed image which effectively eliminates the residual fog and Halo phenomenon has a good color fidelity in the sky region, and also improves the computational speed effectively.