Contrast Restoration of Hazy Image in HSV Space

In this paper, a new haze restoration algorithm is proposed to recover hazy images. Hazy images always suffer from color distortion, detail-information loss and contrast reduction, which degrade the visual quality of the image seriously. To address the issue, this paper introduces an effective and robust hazy image enhancement method without any dedicated hardware or prior knowledge. Firstly, the scene depth can be estimated based on the dark channel prior. Additionally, the saturation and brightness are adaptively corrected according to the scene depth. Finally, the gradient algorithm is used to obtain a better restored result. A large number of experiments are conducted, which demonstrates the superior performance of the proposed method compared with other state-of-the-art techniques in terms of both subjective and objective evaluations.

I. Introduction

Images obtained in outdoor scenes are usually affected by the degradation of atmosphere between the observer and the objects in the scene. The light of the object is absorbed by the suspended particles in the air, which will decrease the contrast of the image and cause color distortion, reducing the visual quality. However, many computer vision applications, such as visual navigation, require more precise input to achieve more efficient processing [1], [2]. Effective dehazing methods urgently needed in practical applications have attracted more and more attention in imaging science in recent years.