Shadow detection using object area-based and morphological filtering for very high-resolution satellite imagery of urban areas
Autor(a) principal: | |
---|---|
Data de Publicação: | 2019 |
Outros Autores: | , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://hdl.handle.net/11449/183281 |
Resumo: | The presence of shadows in remote sensing images leads to misinterpretation of objects and a wrong discrimination of the targets of interest, therefore, limiting the use of several imaging applications. An automatic area-based approach for shadow detection is proposed, which combines spatial and spectral features into a unified and flexible approach. Potential shadow-pixels candidates are identified using morphological-based operators, in particular, black-top-hat transformations as well as area injunction strategies as computed by the well-established normalized saturation-value difference index. The obtained output is a shadow mask, refined in the last step of our method in order to reduce misclassified pixels. Experiments over a large dataset formed by more than 200 scenes of very high-resolution images covering the metropolitan urban area of São Paulo city are performed, where the images are collected from the WorldView-2 (WV-2) and Pléiades-1B (PL-1B) sensors. As verified by an extensive battery of tests, the proposed method provides a good level of discrimination between shadow and nonshadow pixels, with an overall accuracy up to 94.2%, for WV-2, and 90.84%, for PL-1B. Comparative results also attested that the designed approach is very competitive against representative state-of-the-art methods and it can be used for further shadow removal-dependent applications. |
id |
UNSP_668aec4ab66c0169c9ffd46c3450341c |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/183281 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Shadow detection using object area-based and morphological filtering for very high-resolution satellite imagery of urban areasShadow detectionMorphological filteringHigh-resolution imageryUrban remote sensingThe presence of shadows in remote sensing images leads to misinterpretation of objects and a wrong discrimination of the targets of interest, therefore, limiting the use of several imaging applications. An automatic area-based approach for shadow detection is proposed, which combines spatial and spectral features into a unified and flexible approach. Potential shadow-pixels candidates are identified using morphological-based operators, in particular, black-top-hat transformations as well as area injunction strategies as computed by the well-established normalized saturation-value difference index. The obtained output is a shadow mask, refined in the last step of our method in order to reduce misclassified pixels. Experiments over a large dataset formed by more than 200 scenes of very high-resolution images covering the metropolitan urban area of São Paulo city are performed, where the images are collected from the WorldView-2 (WV-2) and Pléiades-1B (PL-1B) sensors. As verified by an extensive battery of tests, the proposed method provides a good level of discrimination between shadow and nonshadow pixels, with an overall accuracy up to 94.2%, for WV-2, and 90.84%, for PL-1B. Comparative results also attested that the designed approach is very competitive against representative state-of-the-art methods and it can be used for further shadow removal-dependent applications.Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)PostprintUniv. Federal de Itajubá (Brazil)Univ. Estadual Paulista "Júlio de Mesquita Filho" (Brazil)FAPESP: 2017/03595-6Society of Photo-optical Instrumentation EngineersUniversidade Estadual Paulista (Unesp)Da Silva, Erivaldo Antonio [UNESP]Colnago, Marilaine [UNESP]Azevedo, Samara Calcado deNegri, Rogerio Galante [UNESP]Casaca, Wallace [UNESP]2019-08-23T12:53:44Z2019-08-23T12:53:44Z2019-08-09info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfJournal of Applied Remote Sensing. v. 13, n. 3, jul. 2019.1931-3195http://hdl.handle.net/11449/18328110.1117/1.JRS.13.036506910354500450713587642258152530911997144653965010820180513298128832721212237335920000-0002-7069-04790000-0003-1599-491X0000-0002-4808-23620000-0002-1073-9939engJournal of Applied Remote Sensinginfo:eu-repo/semantics/openAccessreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESP2024-06-18T15:01:28Zoai:repositorio.unesp.br:11449/183281Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-06-18T15:01:28Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Shadow detection using object area-based and morphological filtering for very high-resolution satellite imagery of urban areas |
title |
Shadow detection using object area-based and morphological filtering for very high-resolution satellite imagery of urban areas |
spellingShingle |
Shadow detection using object area-based and morphological filtering for very high-resolution satellite imagery of urban areas Da Silva, Erivaldo Antonio [UNESP] Shadow detection Morphological filtering High-resolution imagery Urban remote sensing |
title_short |
Shadow detection using object area-based and morphological filtering for very high-resolution satellite imagery of urban areas |
title_full |
Shadow detection using object area-based and morphological filtering for very high-resolution satellite imagery of urban areas |
title_fullStr |
Shadow detection using object area-based and morphological filtering for very high-resolution satellite imagery of urban areas |
title_full_unstemmed |
Shadow detection using object area-based and morphological filtering for very high-resolution satellite imagery of urban areas |
title_sort |
Shadow detection using object area-based and morphological filtering for very high-resolution satellite imagery of urban areas |
author |
Da Silva, Erivaldo Antonio [UNESP] |
author_facet |
Da Silva, Erivaldo Antonio [UNESP] Colnago, Marilaine [UNESP] Azevedo, Samara Calcado de Negri, Rogerio Galante [UNESP] Casaca, Wallace [UNESP] |
author_role |
author |
author2 |
Colnago, Marilaine [UNESP] Azevedo, Samara Calcado de Negri, Rogerio Galante [UNESP] Casaca, Wallace [UNESP] |
author2_role |
author author author author |
dc.contributor.none.fl_str_mv |
Universidade Estadual Paulista (Unesp) |
dc.contributor.author.fl_str_mv |
Da Silva, Erivaldo Antonio [UNESP] Colnago, Marilaine [UNESP] Azevedo, Samara Calcado de Negri, Rogerio Galante [UNESP] Casaca, Wallace [UNESP] |
dc.subject.por.fl_str_mv |
Shadow detection Morphological filtering High-resolution imagery Urban remote sensing |
topic |
Shadow detection Morphological filtering High-resolution imagery Urban remote sensing |
description |
The presence of shadows in remote sensing images leads to misinterpretation of objects and a wrong discrimination of the targets of interest, therefore, limiting the use of several imaging applications. An automatic area-based approach for shadow detection is proposed, which combines spatial and spectral features into a unified and flexible approach. Potential shadow-pixels candidates are identified using morphological-based operators, in particular, black-top-hat transformations as well as area injunction strategies as computed by the well-established normalized saturation-value difference index. The obtained output is a shadow mask, refined in the last step of our method in order to reduce misclassified pixels. Experiments over a large dataset formed by more than 200 scenes of very high-resolution images covering the metropolitan urban area of São Paulo city are performed, where the images are collected from the WorldView-2 (WV-2) and Pléiades-1B (PL-1B) sensors. As verified by an extensive battery of tests, the proposed method provides a good level of discrimination between shadow and nonshadow pixels, with an overall accuracy up to 94.2%, for WV-2, and 90.84%, for PL-1B. Comparative results also attested that the designed approach is very competitive against representative state-of-the-art methods and it can be used for further shadow removal-dependent applications. |
publishDate |
2019 |
dc.date.none.fl_str_mv |
2019-08-23T12:53:44Z 2019-08-23T12:53:44Z 2019-08-09 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
Journal of Applied Remote Sensing. v. 13, n. 3, jul. 2019. 1931-3195 http://hdl.handle.net/11449/183281 10.1117/1.JRS.13.036506 9103545004507135 8764225815253091 1997144653965010 8201805132981288 3272121223733592 0000-0002-7069-0479 0000-0003-1599-491X 0000-0002-4808-2362 0000-0002-1073-9939 |
identifier_str_mv |
Journal of Applied Remote Sensing. v. 13, n. 3, jul. 2019. 1931-3195 10.1117/1.JRS.13.036506 9103545004507135 8764225815253091 1997144653965010 8201805132981288 3272121223733592 0000-0002-7069-0479 0000-0003-1599-491X 0000-0002-4808-2362 0000-0002-1073-9939 |
url |
http://hdl.handle.net/11449/183281 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Journal of Applied Remote Sensing |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
Society of Photo-optical Instrumentation Engineers |
publisher.none.fl_str_mv |
Society of Photo-optical Instrumentation Engineers |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
|
_version_ |
1803045353776218112 |