Image Dehazing using Dark and Bright Channel Priors and Multi-scale Filters

Abstract

The paper proposes bright and dark channel priors dependent single image based dehazing in two color spaces. The hazy RGB is first converted into YC b C r space. Transmission maps are estimated using dark channel priors (DCPs) and airlight of intensity (in YC b C r ) and RGB components computed using three window sizes. Bright channel priors (BCPs) and threshold values are also computed for YC b C r and RGB color spaces. The transmission maps are adjusted using DCPs and BCPs and refined using multiscale guided filter to obtain a superior dehazed image. Comparison (both visually and qualitatively) on variety of images exhibits the significance of proposed technique over existing techniques.