Abstract: In single image, to recover the image in the foggy weather faster,and to make it suitable for both foggy and haze weather. The method of dark channel prior and the Retinex based on the theory of human vision were combined and improved. The method of estimating the atmospheric light in the dark channel prior is improved, and the color of haze image is rectified, which make it suitable for both the fog and haze image. In addition, the estimating of the transmissivity in the method of dark channel prior is simplified. On this basis, the simplified dark channel prior method and the Retinex algorithm are combined, which achieved real-time processing the fog and haze image. Based upon the experiment, this method has preferable efficiency on processing the fog and haze image in the application of monitoring road, while the real-time speed is also guaranteed.

Key words: fog and haze, dark channel prior, atmospheric light, Retinex, monitoring road