Classification guided thick fog removal network for drone imaging: ClassifyCycle

Abstract

The foggy images captured by drones are nonuniform due to inhomogeneous distribution of fog in higher altitude, leading to the obvious fog thickness differences in the images. This paper proposes a classification guided thick fog removal network for drone imaging, termed ClassifyCycle. The drone images are input into the proposed classification module (ICLFn) to enhance the reliability of follow-up learning network. The style migration module (ISMn) is introduced to reduce the image distortion, such as hue artifact and texture distort. The proposed network ClassifyCycle does not require paired foggy and corresponding fog-free datasets, avoiding the phenomena of overexposure, distortion, color deviation and fog residue after defogging. Extensive experimental results show that the proposed ClassifyCycle network surpasses the state-of-the-art algorithms on synthetic and realistic drone images captured in thick fog weather.