Single haze removal method using peplography

In this paper, we propose a single haze removal method using a peplography algorithm to enhance the applicability of conventional peplography. In conventional peplography, it can visualize the objects under dense haze conditions by using statistical haze estimation and photon counting algorithm. However, because this method may not visualize objects under real-world conditions with colorful and complex environments, the loss of information for the objects and severe background noise may be generated. It means that the conventional peplography has low applicability such as autonomous driving, robotics, and so on. To improve visual quality and applicability, in this paper, mask processing that can amplify the non-haze information in frequency domain is used. To verify the feasibility of our proposed method, we implement the experiment with real-world haze images from DENSE-HAZE dataset and show the performance of no-reference image quality assessment (NR-IQA) methods such as blind/referenceless image spatial quality evaluator (BRISQUE), naturalness image quality evaluator (NIQE), and perception based image quality evaluator (PIQE).