Single image fog removal algorithm based on an improved dark channel prior method

Abstract

Recently, how to make surveillance cameras running in all weather conditions become a very important research topic. Because surveillance images are often influenced by the weather conditions in a real world. In this paper, a fast single image fog removal algorithm based on an improved dark channel prior method is proposed. Compared to the latest works, the proposed algorithm can increase 28.5% computing speed and 41.8% image contrast ratio. Meanwhile, it can remove fog efficiently without the influence in the night too.