Research Of Image Defogging Algorithm Based On The Polarization Information

Haze weather is more and more common. It has resulted in reducing the application value of the collected image. So how to obtain high-definition images becomes the research focus in the field of computer vision and other areas. Research of image defogging algorithm based on the polarization information is more and more becoming a hot topic in recent years. This algorithm can be widely applied and developed in visual systems such as traffic monitoring, aerial photography, military target detection and recognition, etc. It has important research significance.Based on atmospheric scattering model, combining with the advantages of polarization imaging, an image defogging method using image polarization information is adopted. The method firstly acquires 3 random angles or 2 orthogonal angles polarization images using polarization imaging system. Then automatically estimates the atmospheric light intensity information and transmission rate combined with the dark channel prior. And guided filter method is used to optimize transmission rate, ultimately realizes image defogging.Image defogging effect of classic polarization image defogging algorithm and the proposed algorithm are analyzed and compared in the experiment. In the meantime, polarization image restoration quality of 3 random angles and 2 orthogonal angles are also compared in the experiment. Experimental results have shown that the algorithm improves the image's definition and contrast. It effectively improves degraded images in the haze condition. And the angles of 3 polarization images are arbitrary. It is not necessary to carry on the registration of the polarization angle. It is beneficial to the practical application of the engineering. The superiority and practicability of this proposed algorithm are verified.