关键词: 暗通道, 补偿算法, 白平衡, 图像融合

Abstract: 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.

Key words: dark channel, compensation algorithm, white balance, image fusion