Use of sampling polygons in supervisioned classifications of satellite images
Autor(a) principal: | |
---|---|
Data de Publicação: | 2019 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | por |
Título da fonte: | Entre-Lugar (Online) |
Texto Completo: | https://ojs.ufgd.edu.br/entre-lugar/article/view/9595 |
Resumo: | The territory dynamics has always been prominent in geographic and, more precisely, environmental research. Different methods and techniques can be used to perform these studies, among them, it is possible to highlight the application of remote sensing techniques with the use of orbital satellite images. This study aimed to analyze the data obtained through the relationship between the dimensions of the classified areas and the increasing number of sampling polygons, based on the supervised classification of satellite images using training areas or polygon clusters. Experiments were carried out with three classes for the years 1985 and 2018, namely water bodies, anthropic areas and "original" vegetation cover. The simulations carried out confirmed the hypothesis presented, i.e., that there would be a trend of stabilization in the data according to the increase of training areas. As a recommendation for future classifications, it is suggested to adopt at least fifty sample polygons per class, which best defines the region to be classified, since such areas of training should cover all the characteristics related to the classes to be adopted. |
id |
UFGD-5_5491e5ffae49231e87bcc8bd5fcf355d |
---|---|
oai_identifier_str |
oai:ojs.pkp.sfu.ca:article/9595 |
network_acronym_str |
UFGD-5 |
network_name_str |
Entre-Lugar (Online) |
repository_id_str |
|
spelling |
Use of sampling polygons in supervisioned classifications of satellite imagesO uso de polígonos de amostragem em classificações supervisionadas de imagens de satéliteRemote sensing. Classification of satellite images. Training áreas. Cluster of polygons. Number of samples.Sensoriamento remoto. Classificação supervisionada. Áreas de treinamento. Polígonos de amostragem. Cluster de polígonos.The territory dynamics has always been prominent in geographic and, more precisely, environmental research. Different methods and techniques can be used to perform these studies, among them, it is possible to highlight the application of remote sensing techniques with the use of orbital satellite images. This study aimed to analyze the data obtained through the relationship between the dimensions of the classified areas and the increasing number of sampling polygons, based on the supervised classification of satellite images using training areas or polygon clusters. Experiments were carried out with three classes for the years 1985 and 2018, namely water bodies, anthropic areas and "original" vegetation cover. The simulations carried out confirmed the hypothesis presented, i.e., that there would be a trend of stabilization in the data according to the increase of training areas. As a recommendation for future classifications, it is suggested to adopt at least fifty sample polygons per class, which best defines the region to be classified, since such areas of training should cover all the characteristics related to the classes to be adopted.A dinâmica existente no território sempre ocupou destaque em pesquisas geográficas e, mais precisamente, ambientais. Diferentes métodos e técnicas podem ser utilizados para a realização destes estudos e, entre eles, pode-se destacar a aplicação das técnicas do sensoriamento remoto com o uso de imagens de satélites orbitais. Logo, este estudo buscou, a partir da classificação supervisionada de imagens do satélite Landsat com o uso de áreas de treinamento, ou clusters de polígonos, analisar os dados obtidos através da relação entre as dimensões das áreas classificadas com o incremento de polígonos de amostragem. Foram realizadas experimentações com três classes para os anos de 1985 e de 2018, a saber, corpos d’água, áreas antropizadas e cobertura vegetal “original”. As simulações realizadas confirmaram a hipótese apresentada, ou seja, a de que haveria uma tendência de estabilização nos dados de acordo com o incremento de áreas de treinamento. Como recomendação para futuras classificações, sugere-se a adoção de, pelo menos, cinquenta polígonos amostrais por classe, que configurem, da melhor forma possível, a região a ser classificada uma vez que tais áreas de treinamento deverão abarcar todas as características relativas às classes a serem adotadas.Editora da Universidade Federal da Grande Dourados2019-07-30info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://ojs.ufgd.edu.br/entre-lugar/article/view/959510.30612/el.v10i19.9595ENTRE-LUGAR; v. 10 n. 19 (2019); 319-3412177-78292176-9559reponame:Entre-Lugar (Online)instname:Universidade Federal da Grande Dourados (UFGD)instacron:UFGDporhttps://ojs.ufgd.edu.br/entre-lugar/article/view/9595/5214Copyright (c) 2019 ENTRE-LUGARinfo:eu-repo/semantics/openAccessFitz, Paulo RobertoVieira, Jeferson CordeiroSoares, Mirlla Casimiro2019-08-02T16:20:03Zoai:ojs.pkp.sfu.ca:article/9595Revistahttps://ojs.ufgd.edu.br/index.php/entre-lugarPUBhttps://ojs.ufgd.edu.br/index.php/entre-lugar/oaimarcosmondardo@yahoo.com.br||charleisilva@ufgd.edu.br||editora.suporte@ufgd.edu.br10.306122177-78292176-9559opendoar:2019-08-02T16:20:03Entre-Lugar (Online) - Universidade Federal da Grande Dourados (UFGD)false |
dc.title.none.fl_str_mv |
Use of sampling polygons in supervisioned classifications of satellite images O uso de polígonos de amostragem em classificações supervisionadas de imagens de satélite |
title |
Use of sampling polygons in supervisioned classifications of satellite images |
spellingShingle |
Use of sampling polygons in supervisioned classifications of satellite images Fitz, Paulo Roberto Remote sensing. Classification of satellite images. Training áreas. Cluster of polygons. Number of samples. Sensoriamento remoto. Classificação supervisionada. Áreas de treinamento. Polígonos de amostragem. Cluster de polígonos. |
title_short |
Use of sampling polygons in supervisioned classifications of satellite images |
title_full |
Use of sampling polygons in supervisioned classifications of satellite images |
title_fullStr |
Use of sampling polygons in supervisioned classifications of satellite images |
title_full_unstemmed |
Use of sampling polygons in supervisioned classifications of satellite images |
title_sort |
Use of sampling polygons in supervisioned classifications of satellite images |
author |
Fitz, Paulo Roberto |
author_facet |
Fitz, Paulo Roberto Vieira, Jeferson Cordeiro Soares, Mirlla Casimiro |
author_role |
author |
author2 |
Vieira, Jeferson Cordeiro Soares, Mirlla Casimiro |
author2_role |
author author |
dc.contributor.author.fl_str_mv |
Fitz, Paulo Roberto Vieira, Jeferson Cordeiro Soares, Mirlla Casimiro |
dc.subject.por.fl_str_mv |
Remote sensing. Classification of satellite images. Training áreas. Cluster of polygons. Number of samples. Sensoriamento remoto. Classificação supervisionada. Áreas de treinamento. Polígonos de amostragem. Cluster de polígonos. |
topic |
Remote sensing. Classification of satellite images. Training áreas. Cluster of polygons. Number of samples. Sensoriamento remoto. Classificação supervisionada. Áreas de treinamento. Polígonos de amostragem. Cluster de polígonos. |
description |
The territory dynamics has always been prominent in geographic and, more precisely, environmental research. Different methods and techniques can be used to perform these studies, among them, it is possible to highlight the application of remote sensing techniques with the use of orbital satellite images. This study aimed to analyze the data obtained through the relationship between the dimensions of the classified areas and the increasing number of sampling polygons, based on the supervised classification of satellite images using training areas or polygon clusters. Experiments were carried out with three classes for the years 1985 and 2018, namely water bodies, anthropic areas and "original" vegetation cover. The simulations carried out confirmed the hypothesis presented, i.e., that there would be a trend of stabilization in the data according to the increase of training areas. As a recommendation for future classifications, it is suggested to adopt at least fifty sample polygons per class, which best defines the region to be classified, since such areas of training should cover all the characteristics related to the classes to be adopted. |
publishDate |
2019 |
dc.date.none.fl_str_mv |
2019-07-30 |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
https://ojs.ufgd.edu.br/entre-lugar/article/view/9595 10.30612/el.v10i19.9595 |
url |
https://ojs.ufgd.edu.br/entre-lugar/article/view/9595 |
identifier_str_mv |
10.30612/el.v10i19.9595 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.relation.none.fl_str_mv |
https://ojs.ufgd.edu.br/entre-lugar/article/view/9595/5214 |
dc.rights.driver.fl_str_mv |
Copyright (c) 2019 ENTRE-LUGAR info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
Copyright (c) 2019 ENTRE-LUGAR |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
Editora da Universidade Federal da Grande Dourados |
publisher.none.fl_str_mv |
Editora da Universidade Federal da Grande Dourados |
dc.source.none.fl_str_mv |
ENTRE-LUGAR; v. 10 n. 19 (2019); 319-341 2177-7829 2176-9559 reponame:Entre-Lugar (Online) instname:Universidade Federal da Grande Dourados (UFGD) instacron:UFGD |
instname_str |
Universidade Federal da Grande Dourados (UFGD) |
instacron_str |
UFGD |
institution |
UFGD |
reponame_str |
Entre-Lugar (Online) |
collection |
Entre-Lugar (Online) |
repository.name.fl_str_mv |
Entre-Lugar (Online) - Universidade Federal da Grande Dourados (UFGD) |
repository.mail.fl_str_mv |
marcosmondardo@yahoo.com.br||charleisilva@ufgd.edu.br||editora.suporte@ufgd.edu.br |
_version_ |
1809280510296326144 |