An Adaptive Dark Channel Dehazing Algorithm Based on Airspace Proportion
Aiming at the problem of color distortion in the sky region existing in the dark channel dehazing algorithm,an adaptive dark channel dehazing algorithm based on the proportion of airspace has been proposed.Firstly,the threshold iteration method is introduced into the algorithm to adaptively segment the sky area of the foggy image;then the proportion of the airspace of the foggy image is calculated.When the proportion is larger than the set threshold of 0.05,the average value of the top 1%of the highest brightness pixels in the sky area is regarded as the atmospheric light value,otherwise the weighted average is used to obtain the global atmospheric light value;for the non-sky area,the transmittance is still calculated according to the dark channel prior,and the correction factor is introduced into the sky area,and adaptively correct the sky region transmittance while refining it with guided filtering;finally,the haze-free image is recovered by an atmospheric scattering model.The experimental results show that the proposed algorithm improves the color distortion in the sky area,which effectively removes the fog of the image and restores the detailed information of the image,and the time complexity is reduced,which has certain advantages.
国家科技期刊平台
NSTL
万方数据
维普
