Algorithm of Removing Thin Cloud-fog Cover from Single Remote Sensing Image

摘要

To remove thin cloud-fog cover from single remote sensing image efficiently, a new algorithm based on dark channel prior is proposed. Firstly, the atmospheric veil is preliminarily estimated by the dark channel period theory rather than defined as the minimal components of original image. And then, a Gaussian low-pass filter and a feedback mechanism are applied to refine the preliminary estimated atmospheric veil, which can eliminate the uneven fog-cloud cover efficiently. Subsequently, the atmospheric veil is further refined by the guided image filter under the guidance of the original image, which can preserve the detail information. Finally, the experiment results show the proposed algorithm can remove the thin cloud-fog cover from single remote sensing image effectively and improve the image visibility greatly.