Eintrag weiter verarbeiten
FULLY CONVOLUTIONAL NETWORK BASED SHADOW EXTRACTION FROM GF-2 IMAGERY
Gespeichert in:
Zeitschriftentitel: | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
---|---|
Personen und Körperschaften: | , , |
In: | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLII-3, 2018, S. 985-991 |
Format: | E-Article |
Sprache: | Englisch |
veröffentlicht: |
Copernicus GmbH
|
Schlagwörter: |
author_facet |
Li, Z. Cai, G. Ren, H. Li, Z. Cai, G. Ren, H. |
---|---|
author |
Li, Z. Cai, G. Ren, H. |
spellingShingle |
Li, Z. Cai, G. Ren, H. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences FULLY CONVOLUTIONAL NETWORK BASED SHADOW EXTRACTION FROM GF-2 IMAGERY General Earth and Planetary Sciences General Environmental Science |
author_sort |
li, z. |
spelling |
Li, Z. Cai, G. Ren, H. 2194-9034 Copernicus GmbH General Earth and Planetary Sciences General Environmental Science http://dx.doi.org/10.5194/isprs-archives-xlii-3-985-2018 <jats:p>Abstract. There are many shadows on the high spatial resolution satellite images, especially in the urban areas. Although shadows on imagery severely affect the information extraction of land cover or land use, they provide auxiliary information for building extraction which is hard to achieve a satisfactory accuracy through image classification itself. This paper focused on the method of building shadow extraction by designing a fully convolutional network and training samples collected from GF-2 satellite imagery in the urban region of Changchun city. By means of spatial filtering and calculation of adjacent relationship along the sunlight direction, the small patches from vegetation or bridges have been eliminated from the preliminary extracted shadows. Finally, the building shadows were separated. The extracted building shadow information from the proposed method in this paper was compared with the results from the traditional object-oriented supervised classification algorihtms. It showed that the deep learning network approach can improve the accuracy to a large extent. </jats:p> FULLY CONVOLUTIONAL NETWORK BASED SHADOW EXTRACTION FROM GF-2 IMAGERY The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
doi_str_mv |
10.5194/isprs-archives-xlii-3-985-2018 |
facet_avail |
Online Free |
format |
ElectronicArticle |
fullrecord |
blob:ai-49-aHR0cDovL2R4LmRvaS5vcmcvMTAuNTE5NC9pc3Bycy1hcmNoaXZlcy14bGlpLTMtOTg1LTIwMTg |
id |
ai-49-aHR0cDovL2R4LmRvaS5vcmcvMTAuNTE5NC9pc3Bycy1hcmNoaXZlcy14bGlpLTMtOTg1LTIwMTg |
institution |
DE-D275 DE-Bn3 DE-Brt1 DE-Zwi2 DE-D161 DE-Gla1 DE-Zi4 DE-15 DE-Rs1 DE-Pl11 DE-105 DE-14 DE-Ch1 DE-L229 |
imprint |
Copernicus GmbH, 2018 |
imprint_str_mv |
Copernicus GmbH, 2018 |
issn |
2194-9034 |
issn_str_mv |
2194-9034 |
language |
English |
mega_collection |
Copernicus GmbH (CrossRef) |
match_str |
li2018fullyconvolutionalnetworkbasedshadowextractionfromgf2imagery |
publishDateSort |
2018 |
publisher |
Copernicus GmbH |
recordtype |
ai |
record_format |
ai |
series |
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
source_id |
49 |
title |
FULLY CONVOLUTIONAL NETWORK BASED SHADOW EXTRACTION FROM GF-2 IMAGERY |
title_unstemmed |
FULLY CONVOLUTIONAL NETWORK BASED SHADOW EXTRACTION FROM GF-2 IMAGERY |
title_full |
FULLY CONVOLUTIONAL NETWORK BASED SHADOW EXTRACTION FROM GF-2 IMAGERY |
title_fullStr |
FULLY CONVOLUTIONAL NETWORK BASED SHADOW EXTRACTION FROM GF-2 IMAGERY |
title_full_unstemmed |
FULLY CONVOLUTIONAL NETWORK BASED SHADOW EXTRACTION FROM GF-2 IMAGERY |
title_short |
FULLY CONVOLUTIONAL NETWORK BASED SHADOW EXTRACTION FROM GF-2 IMAGERY |
title_sort |
fully convolutional network based shadow extraction from gf-2 imagery |
topic |
General Earth and Planetary Sciences General Environmental Science |
url |
http://dx.doi.org/10.5194/isprs-archives-xlii-3-985-2018 |
publishDate |
2018 |
physical |
985-991 |
description |
<jats:p>Abstract. There are many shadows on the high spatial resolution satellite images, especially in the urban areas. Although shadows on imagery severely affect the information extraction of land cover or land use, they provide auxiliary information for building extraction which is hard to achieve a satisfactory accuracy through image classification itself. This paper focused on the method of building shadow extraction by designing a fully convolutional network and training samples collected from GF-2 satellite imagery in the urban region of Changchun city. By means of spatial filtering and calculation of adjacent relationship along the sunlight direction, the small patches from vegetation or bridges have been eliminated from the preliminary extracted shadows. Finally, the building shadows were separated. The extracted building shadow information from the proposed method in this paper was compared with the results from the traditional object-oriented supervised classification algorihtms. It showed that the deep learning network approach can improve the accuracy to a large extent.
</jats:p> |
container_start_page |
985 |
container_title |
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
container_volume |
XLII-3 |
format_de105 |
Article, E-Article |
format_de14 |
Article, E-Article |
format_de15 |
Article, E-Article |
format_de520 |
Article, E-Article |
format_de540 |
Article, E-Article |
format_dech1 |
Article, E-Article |
format_ded117 |
Article, E-Article |
format_degla1 |
E-Article |
format_del152 |
Buch |
format_del189 |
Article, E-Article |
format_dezi4 |
Article |
format_dezwi2 |
Article, E-Article |
format_finc |
Article, E-Article |
format_nrw |
Article, E-Article |
_version_ |
1792330434872344581 |
geogr_code |
not assigned |
last_indexed |
2024-03-01T13:25:01.901Z |
geogr_code_person |
not assigned |
openURL |
url_ver=Z39.88-2004&ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fvufind.svn.sourceforge.net%3Agenerator&rft.title=FULLY+CONVOLUTIONAL+NETWORK+BASED+SHADOW+EXTRACTION+FROM+GF-2+IMAGERY&rft.date=2018-04-30&genre=article&issn=2194-9034&volume=XLII-3&spage=985&epage=991&pages=985-991&jtitle=The+International+Archives+of+the+Photogrammetry%2C+Remote+Sensing+and+Spatial+Information+Sciences&atitle=FULLY+CONVOLUTIONAL+NETWORK+BASED+SHADOW+EXTRACTION+FROM+GF-2+IMAGERY&aulast=Ren&aufirst=H.&rft_id=info%3Adoi%2F10.5194%2Fisprs-archives-xlii-3-985-2018&rft.language%5B0%5D=eng |
SOLR | |
_version_ | 1792330434872344581 |
author | Li, Z., Cai, G., Ren, H. |
author_facet | Li, Z., Cai, G., Ren, H., Li, Z., Cai, G., Ren, H. |
author_sort | li, z. |
container_start_page | 985 |
container_title | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
container_volume | XLII-3 |
description | <jats:p>Abstract. There are many shadows on the high spatial resolution satellite images, especially in the urban areas. Although shadows on imagery severely affect the information extraction of land cover or land use, they provide auxiliary information for building extraction which is hard to achieve a satisfactory accuracy through image classification itself. This paper focused on the method of building shadow extraction by designing a fully convolutional network and training samples collected from GF-2 satellite imagery in the urban region of Changchun city. By means of spatial filtering and calculation of adjacent relationship along the sunlight direction, the small patches from vegetation or bridges have been eliminated from the preliminary extracted shadows. Finally, the building shadows were separated. The extracted building shadow information from the proposed method in this paper was compared with the results from the traditional object-oriented supervised classification algorihtms. It showed that the deep learning network approach can improve the accuracy to a large extent. </jats:p> |
doi_str_mv | 10.5194/isprs-archives-xlii-3-985-2018 |
facet_avail | Online, Free |
format | ElectronicArticle |
format_de105 | Article, E-Article |
format_de14 | Article, E-Article |
format_de15 | Article, E-Article |
format_de520 | Article, E-Article |
format_de540 | Article, E-Article |
format_dech1 | Article, E-Article |
format_ded117 | Article, E-Article |
format_degla1 | E-Article |
format_del152 | Buch |
format_del189 | Article, E-Article |
format_dezi4 | Article |
format_dezwi2 | Article, E-Article |
format_finc | Article, E-Article |
format_nrw | Article, E-Article |
geogr_code | not assigned |
geogr_code_person | not assigned |
id | ai-49-aHR0cDovL2R4LmRvaS5vcmcvMTAuNTE5NC9pc3Bycy1hcmNoaXZlcy14bGlpLTMtOTg1LTIwMTg |
imprint | Copernicus GmbH, 2018 |
imprint_str_mv | Copernicus GmbH, 2018 |
institution | DE-D275, DE-Bn3, DE-Brt1, DE-Zwi2, DE-D161, DE-Gla1, DE-Zi4, DE-15, DE-Rs1, DE-Pl11, DE-105, DE-14, DE-Ch1, DE-L229 |
issn | 2194-9034 |
issn_str_mv | 2194-9034 |
language | English |
last_indexed | 2024-03-01T13:25:01.901Z |
match_str | li2018fullyconvolutionalnetworkbasedshadowextractionfromgf2imagery |
mega_collection | Copernicus GmbH (CrossRef) |
physical | 985-991 |
publishDate | 2018 |
publishDateSort | 2018 |
publisher | Copernicus GmbH |
record_format | ai |
recordtype | ai |
series | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
source_id | 49 |
spelling | Li, Z. Cai, G. Ren, H. 2194-9034 Copernicus GmbH General Earth and Planetary Sciences General Environmental Science http://dx.doi.org/10.5194/isprs-archives-xlii-3-985-2018 <jats:p>Abstract. There are many shadows on the high spatial resolution satellite images, especially in the urban areas. Although shadows on imagery severely affect the information extraction of land cover or land use, they provide auxiliary information for building extraction which is hard to achieve a satisfactory accuracy through image classification itself. This paper focused on the method of building shadow extraction by designing a fully convolutional network and training samples collected from GF-2 satellite imagery in the urban region of Changchun city. By means of spatial filtering and calculation of adjacent relationship along the sunlight direction, the small patches from vegetation or bridges have been eliminated from the preliminary extracted shadows. Finally, the building shadows were separated. The extracted building shadow information from the proposed method in this paper was compared with the results from the traditional object-oriented supervised classification algorihtms. It showed that the deep learning network approach can improve the accuracy to a large extent. </jats:p> FULLY CONVOLUTIONAL NETWORK BASED SHADOW EXTRACTION FROM GF-2 IMAGERY The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
spellingShingle | Li, Z., Cai, G., Ren, H., The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, FULLY CONVOLUTIONAL NETWORK BASED SHADOW EXTRACTION FROM GF-2 IMAGERY, General Earth and Planetary Sciences, General Environmental Science |
title | FULLY CONVOLUTIONAL NETWORK BASED SHADOW EXTRACTION FROM GF-2 IMAGERY |
title_full | FULLY CONVOLUTIONAL NETWORK BASED SHADOW EXTRACTION FROM GF-2 IMAGERY |
title_fullStr | FULLY CONVOLUTIONAL NETWORK BASED SHADOW EXTRACTION FROM GF-2 IMAGERY |
title_full_unstemmed | FULLY CONVOLUTIONAL NETWORK BASED SHADOW EXTRACTION FROM GF-2 IMAGERY |
title_short | FULLY CONVOLUTIONAL NETWORK BASED SHADOW EXTRACTION FROM GF-2 IMAGERY |
title_sort | fully convolutional network based shadow extraction from gf-2 imagery |
title_unstemmed | FULLY CONVOLUTIONAL NETWORK BASED SHADOW EXTRACTION FROM GF-2 IMAGERY |
topic | General Earth and Planetary Sciences, General Environmental Science |
url | http://dx.doi.org/10.5194/isprs-archives-xlii-3-985-2018 |