关键词: 图像去雾, 暗原色, 像素评价, 图像序列分析, 曝光融合

Abstract: This paper proposed a simple and effective method to remove haze from a single input image degraded by bad weather. First, it estimated the airlight by using dark channel prior knowledge. Then, under a mathematical model for describing the formation of a hazy image, the depth of field of each pixel was sampled to get a virtual haze-free image sequence. Finally, an exposure criterion introduced by exposure fusion algorithm was used to extract a haze-free image from the image sequence by multi-scale fashion image fusion method. The experimental results show that the proposed method can yield good results and it is appropriate for real-time applications.

Key words: image dehazing, dark channel prior, pixel assessment, image sequence analysis, exposure fusion