Single Image Dehazing Using Dark Channel Fusion and Dark Channel Confidence

Abstract

Sometimes dark channel prior for single image dehazing algorithms may fail in sky areas and suffer from the darkness and residual artifacts. In this paper, we have proposed a new method to solve these problems which based on dark channel fusion and dark channel confidence. Firstly, the original dark channel and the pixel-wise dark channel is used to obtain the fusion dark channel, secondly we use dark channel confidence to correct for transmittance of the sky area. Experimental results show that the proposed method can obviously eliminate the color cast and distortion phenomenon in sky regions and the details o f restored image become more distinct after removing the residual artifacts.