Record number :
Title of article :
Cloud removal for remotely sensed images by similar pixel replacement guided with a spatio-temporal MRF model
Author/Authors :
Cheng، نويسنده , , Qing and Shen، نويسنده , , Huanfeng and Zhang، نويسنده , , Liangpei and Yuan، نويسنده , , Qiangqiang and Zeng، نويسنده , , Chao، نويسنده ,
Issue Information :
روزنامه با شماره پیاپی سال 2014
Pages :
From page :
To page :
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 paper, an effective method based on similar pixel replacement is developed to solve this task. A missing pixel is filled using an appropriate similar pixel within the remaining region of the target image. A multitemporal image is used as the guidance to locate the similar pixels. A pixel-offset based spatio-temporal Markov random fields (MRF) global function is built to find the most suitable similar pixel. The proposed method was tested on MODIS and Landsat images and their land surface temperature products, and the experiments verify that the proposed method can achieve highly accurate results and is effective at dealing with the obvious atmospheric and seasonal differences between multitemporal images.
Keywords :
Cloud removal , Spatio-temporal MRF , multitemporal , Remotely sensed image , Similar pixel replacement , Information reconstruction
Journal title :
ISPRS Journal of Photogrammetry and Remote Sensing
Journal title :
ISPRS Journal of Photogrammetry and Remote Sensing
Serial Year :
Link To Document :