Abstract: Cloud cover is generally present in remotely sensed images, which limits the potential of the images for ground information extraction. Therefore, removing the clouds and recovering the ground information for the cloud- contaminated images is often necessary in many applications. In this project, propose a cloud removal approach based on image inpainting. The approach removes cloud-contaminated portions of a satellite image and then reconstructs the information of missing data utilizing temporal correlation of multi temporal images. In order to remove the noise in the classified image weighted trimmed median filter is used. It is possible to remove the isolated shadow pixels in the non- shadow area and isolated non-shadow pixels in the shadow area of the classified image. The median filter works by moving through the image pixel by pixel, replacing each value with the median value of neighbouring pixels. Comparisons with existing algorithms our approach achieves better results in terms of misclassification probability and, in particular, to be very effective in cloud removal.

Keywords: Cloud Detection, Remote Sensing, Satellite Imaging, Image inpainting.