Proceedings of the 9th Annual Meeting of Risk Analysis Council of China Association for Disaster Prevention (RAC 2020)

Research on Removal of Cloud Based on Remote Sensing Image of Sentinel-2

Authors
Aru Han, Jiquan Zhang
Corresponding Author
Jiquan Zhang
Available Online 12 April 2021.
DOI
https://doi.org/10.2991/aebmr.k.210409.006How to use a DOI?
Keywords
Cloud Removal, Sentinel-2, Sen2three, Spatio-temporal synthesis
Abstract
Cloud cover is a serious impediment in land surface analysis from Remote Sensing images either causing complete obstruction with loss of information or blurry effects when being semi-transparent (clouds). While thick clouds require complete pixel replacement, cloud removal is fairly challenging as the atmospheric and land-cover information is inter-twined. In this paper, we address this problem and use the Sentinel-2 data and Sen2Three Processer, through progressive replaced with all “bad” pixels in an previous input image and “good” pixels in the subsequent scene to generate the composite output image, the spatio-temporal synthesis of the image at pixel level is realized. Before cloud removal, the image of cloud area is bright, the contrast is small, and the clouds obscure information about the features below; after cloud removal, the features are clearer, the pixel brightness value is reduced, the contrast is improved, and the cloud removal effect is better. The mean value and standard deviation of the image after cloud removal are both smaller, which indicates that the pixel brightness value in the image is reduced, the feature information covered by the cloud is recovered, the feature is relatively clear, and the contrast is improved, which is conducive to visual interpretation of the image and subsequent processing and analysis. Experimental results showed that this process could effectively remove the haze and efficiently improve the traditional methods of images pre-processing. In addition, it is improved the quality and precision of the images greatly.
Open Access
This is an open access article distributed under the CC BY-NC license.

Download article (PDF)

Cite this article

TY  - CONF
AU  - Aru Han
AU  - Jiquan Zhang
PY  - 2021
DA  - 2021/04/12
TI  - Research on Removal of Cloud Based on Remote Sensing Image of Sentinel-2
BT  - Proceedings of the 9th Annual Meeting of Risk Analysis Council of China Association for Disaster Prevention (RAC 2020)
PB  - Atlantis Press
SP  - 41
EP  - 46
SN  - 2352-5428
UR  - https://doi.org/10.2991/aebmr.k.210409.006
DO  - https://doi.org/10.2991/aebmr.k.210409.006
ID  - Han2021
ER  -