Semi-selective image dehazing

In this paper, we propose a new image dehazing method via the semi-selective method. Firstly, we obtain the effect range of the global atmospheric light according to the statistical prior method. Secondly, a relative total variation with adaptive boundary constraint is developed to optimize the transmission. Finally, a semi-selective method is used to select the image with the best visual sense. Experimental results show that our method outperforms state-of-the-art haze removal methods in dehazing visual effects.