Unsupervised single image dehazing — A contour approach

Abstract

Small particles present in the air degrade the visual clarity of images due to light scattering phenomena caused by particles. This degradation of the image is in the context of attenuation of light intensity and poor contrast, which ultimately have an impact on the image’s quality. Thus, image dehazing is a necessity for better visualization and image analysis. The proposed method uses an unsupervised approach to dehaze the image without using any ground truth image or transmission map, which overcomes the necessity of a paired dataset and a true depth map. The majority of current state-of-the-art haze removal approaches observe color shifts in the sky region. By utilizing the contour process and RGB color plane data, the proposed innovative ”ContourDCP” technique can effectively identify the sky area. After applying the Dark Channel Prior (DCP) to obtain the initial transmission map, it is further reformulate through the contour method to achieve an accurate color representation of the sky area during the image dehazing process. We proposed atmospheric light estimation based on the haze concentration present in the Y-plane after conversion from RGB to YCbCr color space. These modified transmission map and atmospheric light are used in the atmospheric scattering model to recover the scene radiance. Performance evaluation of the method shows the robustness of the proposed method compared to existing state-of-the-art methods.