Research of Polarized Image Defogging Technique Based on Dark Channel Priori and Guided Filtering

Abstract In fog weather, aiming at the poor performance of fog removal based on the conventional polarization defogging algorithm, a dense fog removal algorithm based on the polarization principle of dark channel priori and guided filtering is proposed. The polarization information is combined with the primal theory of dark primary for the purpose of combining the polarization information with the defogging model. Then the dark channel principle of the image is obtained using atmospheric scattering model. Finally, the atmosphere is corrected by the guidance filtering algorithm. The experimental results show that the standard deviation, entropy and average gradient of the defogged image are much higher than those of the existing polarization defogging technology. This method can effectively enhance the overall contrast of the image under foggy weather and improve the target recognition ability of polarized images.