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...
Main Authors: | , , , , |
---|---|
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 |