A CLOUD BOUNDARY DETECTION SCHEME COMBINED WITH ASLIC AND CNN USING ZY-3, GF-1/2 SATELLITE IMAGERY

A CLOUD BOUNDARY DETECTION SCHEME COMBINED WITH ASLIC AND CNN USING ZY-3, GF-1/2 SATELLITE IMAGERY

Remote sensing optical image cloud detection is one of the most important problems in remote sensing data processing. Aiming at the information loss caused by cloud cover, a cloud detection method based on convolution neural network (CNN) is presented in this paper. Firstly, a deep CNN network is us...

Full description

Bibliographic Details
Main Authors: Z. Guo, C. Li, Z. Wang, E. Kwok, X. Wei
Format: Article
Language:English
Published: Copernicus Publications 2018-04-01
Series:The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Online Access:https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLII-3/455/2018/isprs-archives-XLII-3-455-2018.pdf
id doaj-133d048c5ae94d728cbc885b4c5c6df4
record_format Article
spelling doaj-133d048c5ae94d728cbc885b4c5c6df42020-11-24T23:18:56ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342018-04-01XLII-345545810.5194/isprs-archives-XLII-3-455-2018A CLOUD BOUNDARY DETECTION SCHEME COMBINED WITH ASLIC AND CNN USING ZY-3, GF-1/2 SATELLITE IMAGERYZ. Guo0Z. Guo1C. Li2Z. Wang3E. Kwok4X. Wei5School of Geomatics, Liaoning Technical University, Fuxin 123000, ChinaSatellite Surveying and Mapping Application Center, National Administration of Surveying, Mapping and Geoinformation, Beijing 100048, ChinaSatellite Surveying and Mapping Application Center, National Administration of Surveying, Mapping and Geoinformation, Beijing 100048, ChinaSchool of Geomatics, Liaoning Technical University, Fuxin 123000, ChinaSchool of Geomatics, Liaoning Technical University, Fuxin 123000, ChinaSchool of Geomatics, Liaoning Technical University, Fuxin 123000, ChinaRemote sensing optical image cloud detection is one of the most important problems in remote sensing data processing. Aiming at the information loss caused by cloud cover, a cloud detection method based on convolution neural network (CNN) is presented in this paper. Firstly, a deep CNN network is used to extract the multi-level feature generation model of cloud from the training samples. Secondly, the adaptive simple linear iterative clustering (ASLIC) method is used to divide the detected images into superpixels. Finally, the probability of each superpixel belonging to the cloud region is predicted by the trained network model, thereby generating a cloud probability map. The typical region of GF-1/2 and ZY-3 were selected to carry out the cloud detection test, and compared with the traditional SLIC method. The experiment results show that the average accuracy of cloud detection is increased by more than 5 %, and it can detected thin-thick cloud and the whole cloud boundary well on different imaging platforms.https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLII-3/455/2018/isprs-archives-XLII-3-455-2018.pdf
collection DOAJ
language English
format Article
sources DOAJ
author Z. Guo
Z. Guo
C. Li
Z. Wang
E. Kwok
X. Wei
spellingShingle Z. Guo
Z. Guo
C. Li
Z. Wang
E. Kwok
X. Wei
A CLOUD BOUNDARY DETECTION SCHEME COMBINED WITH ASLIC AND CNN USING ZY-3, GF-1/2 SATELLITE IMAGERY
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
author_facet Z. Guo
Z. Guo
C. Li
Z. Wang
E. Kwok
X. Wei
author_sort Z. Guo
title A CLOUD BOUNDARY DETECTION SCHEME COMBINED WITH ASLIC AND CNN USING ZY-3, GF-1/2 SATELLITE IMAGERY
title_short A CLOUD BOUNDARY DETECTION SCHEME COMBINED WITH ASLIC AND CNN USING ZY-3, GF-1/2 SATELLITE IMAGERY
title_full A CLOUD BOUNDARY DETECTION SCHEME COMBINED WITH ASLIC AND CNN USING ZY-3, GF-1/2 SATELLITE IMAGERY
title_fullStr A CLOUD BOUNDARY DETECTION SCHEME COMBINED WITH ASLIC AND CNN USING ZY-3, GF-1/2 SATELLITE IMAGERY
title_full_unstemmed A CLOUD BOUNDARY DETECTION SCHEME COMBINED WITH ASLIC AND CNN USING ZY-3, GF-1/2 SATELLITE IMAGERY
title_sort cloud boundary detection scheme combined with aslic and cnn using zy-3, gf-1/2 satellite imagery
publisher Copernicus Publications
series The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
issn 1682-1750
2194-9034
publishDate 2018-04-01
description Remote sensing optical image cloud detection is one of the most important problems in remote sensing data processing. Aiming at the information loss caused by cloud cover, a cloud detection method based on convolution neural network (CNN) is presented in this paper. Firstly, a deep CNN network is used to extract the multi-level feature generation model of cloud from the training samples. Secondly, the adaptive simple linear iterative clustering (ASLIC) method is used to divide the detected images into superpixels. Finally, the probability of each superpixel belonging to the cloud region is predicted by the trained network model, thereby generating a cloud probability map. The typical region of GF-1/2 and ZY-3 were selected to carry out the cloud detection test, and compared with the traditional SLIC method. The experiment results show that the average accuracy of cloud detection is increased by more than 5 %, and it can detected thin-thick cloud and the whole cloud boundary well on different imaging platforms.
url https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLII-3/455/2018/isprs-archives-XLII-3-455-2018.pdf
work_keys_str_mv AT zguo acloudboundarydetectionschemecombinedwithaslicandcnnusingzy3gf12satelliteimagery
AT zguo acloudboundarydetectionschemecombinedwithaslicandcnnusingzy3gf12satelliteimagery
AT cli acloudboundarydetectionschemecombinedwithaslicandcnnusingzy3gf12satelliteimagery
AT zwang acloudboundarydetectionschemecombinedwithaslicandcnnusingzy3gf12satelliteimagery
AT ekwok acloudboundarydetectionschemecombinedwithaslicandcnnusingzy3gf12satelliteimagery
AT xwei acloudboundarydetectionschemecombinedwithaslicandcnnusingzy3gf12satelliteimagery
AT zguo cloudboundarydetectionschemecombinedwithaslicandcnnusingzy3gf12satelliteimagery
AT zguo cloudboundarydetectionschemecombinedwithaslicandcnnusingzy3gf12satelliteimagery
AT cli cloudboundarydetectionschemecombinedwithaslicandcnnusingzy3gf12satelliteimagery
AT zwang cloudboundarydetectionschemecombinedwithaslicandcnnusingzy3gf12satelliteimagery
AT ekwok cloudboundarydetectionschemecombinedwithaslicandcnnusingzy3gf12satelliteimagery
AT xwei cloudboundarydetectionschemecombinedwithaslicandcnnusingzy3gf12satelliteimagery
_version_ 1725579251924598784

Similar Items