부산대학교 도서관

In recent years, various haze removal methods based on atmospheric scattering models have been proposed. Most methods target strong haze images in which light is scattered equally in all color channels. This paper proposes a haze removal method using near-infrared (NIR) images for weak haze images. The proposed method first restores the edges of color images by fusing weighted NIR images. Second, it estimates transmission maps for all color channels based on a wavelength-dependent scattering model and restores the color of the edge-restored image using the estimated transmission maps. Finally, the edge- restored and color-restored images are blended. Qualitative and quantitative evaluations demonstrate that the proposed method can restore edges and colors more naturally in weak haze images than conventional methods.