1. Identificação | |
Tipo de Referência | Artigo em Evento (Conference Proceedings) |
Site | mtc-m16c.sid.inpe.br |
Código do Detentor | isadg {BR SPINPE} ibi 8JMKD3MGPCW/3DT298S |
Identificador | 8JMKD3MGP8W/3BTC27L |
Repositório | sid.inpe.br/mtc-m18/2012/05.17.18.21 |
Última Atualização | 2012:05.17.18.21.46 (UTC) administrator |
Repositório de Metadados | sid.inpe.br/mtc-m18/2012/05.17.18.21.46 |
Última Atualização dos Metadados | 2018:06.04.03.55.40 (UTC) administrator |
ISBN | 978-85-17-00059-1 |
Chave de Citação | AntunesDuar:2012:ChGrUr |
Título | Characterization of the growth of urban areas by means of QuickBird images through object-oriented segmentation |
Formato | On-line. |
Ano | 2012 |
Data de Acesso | 16 maio 2024 |
Tipo Secundário | PRE CI |
Número de Arquivos | 1 |
Tamanho | 1331 KiB |
|
2. Contextualização | |
Autor | 1 Antunes, Alzir Felippe 2 Duarte, A. |
Endereço de e-Mail do Autor | 1 felipe@ufpr.br 2 alby@ufpr.br |
Editor | Feitosa, Raul Queiroz Costa, Gilson Alexandre Ostwald Pedro da Almeida, Cláudia Maria de Fonseca, Leila Maria Garcia Kux, Hermann Johann Heinrich |
Endereço de e-Mail | wanderf@dsr.inpe.br |
Nome do Evento | International Conference on Geographic Object-Based Image Analysis, 4 (GEOBIA). |
Localização do Evento | Rio de Janeiro |
Data | May 7-9, 2012 |
Editora (Publisher) | Instituto Nacional de Pesquisas Espaciais (INPE) |
Cidade da Editora | São José dos Campos |
Páginas | 191-195 |
Título do Livro | Proceedings |
Organização | Instituto Nacional de Pesquisas Espaciais (INPE) |
Histórico (UTC) | 2012-05-17 18:21:46 :: wanderf@dsr.inpe.br -> administrator :: 2012-05-30 13:45:11 :: administrator -> wanderf@dsr.inpe.br :: 2012 2012-06-01 15:12:44 :: wanderf@dsr.inpe.br -> marciana :: 2012 2012-06-12 14:28:25 :: marciana -> seki@dsr.inpe.br :: 2012 2012-06-13 15:55:31 :: seki@dsr.inpe.br -> marciana :: 2012 2012-06-14 15:03:57 :: marciana -> administrator :: 2012 2018-06-04 03:55:40 :: administrator -> :: 2012 |
|
3. Conteúdo e estrutura | |
É a matriz ou uma cópia? | é a matriz |
Estágio do Conteúdo | concluido |
Transferível | 1 |
Palavras-Chave | object-oriented segmentation hierarchical classification Fuzzy Logic high resolution images urban areas mapping |
Resumo | The dynamics and complexity of urban growth call for new ways to guide development in order to guarantee the sustainability of cities and the quality of life of its inhabitants. Rapid urbanization and the growth of large urban centres demand new strategies in urban planning and territorial organisation, especially at present when unplanned urban growth menaces the limited natural environment. The purpose of this paper is to verify the feasibility of high resolution images for recognition and the classification of features indispensable in urban planning. It tries to establish a methodology that could guide and generate thematic as well as analytical maps showing the dynamics of urban growth using the easiest and most reliable way to obtain spatial information from the image. The methodology applied is based on three norms: the organization of knowledge base from the semantic net; generate objects or features by means of image segmentation. In order to identify which descriptors could discriminate better the interest features multivariate statistic and principal components and discriminant analysis techniques were used, as a result potential descriptors were selected. Contextual information is important in creating objects closer to real features of the terrain and thus optimizing the segmentation process; in other words a creation of more realistic objects neither too fragmented nor too generalized. The proposed method will result in the behavior comprehension of relevant objects by estimating color, shape and dimensional parameters, which control the segmentation process. It should improve the vector representation and consequently the quality of the information extracted from high-resolution imagery. Box-plot were generated to evaluate better relationship between classes and object distribution besides descriptive statistics were also calculated to provide variables selection. Finally the classification process was achieved using those previously chosen descriptors to start up the classification process based on hierarchical classification. The image used in this study contains a panchromatic band and four multi spectral bands from the Quickbird sensor. The study is based on an informal settlement by the name of Guarituba, in the town of Piraquara, in the State of Paraná. The area is important as it is the location of springs which supply water to Curitiba, the capital of the State of Paraná, and its Metropolitan areas. The methodology proposed sounds very promising by means of Statistic Degree of Discrimination created based on bi-variate correlation and descriptive statistitics. The graphic Box-plot, was a useful tool to sort out the functions and parameters definition to perform the classification at urban environment. |
Área | SRE |
Tipo | Multitemporal Analysis |
Conteúdo da Pasta doc | acessar |
Conteúdo da Pasta source | não têm arquivos |
Conteúdo da Pasta agreement | não têm arquivos |
|
4. Condições de acesso e uso | |
URL dos dados | http://urlib.net/ibi/8JMKD3MGP8W/3BTC27L |
URL dos dados zipados | http://urlib.net/zip/8JMKD3MGP8W/3BTC27L |
Idioma | en |
Arquivo Alvo | 056.pdf |
Grupo de Usuários | administrator wanderf@dsr.inpe.br |
Visibilidade | shown |
|
5. Fontes relacionadas | |
Repositório Espelho | urlib.net/www/2011/03.29.20.55 |
Acervo Hospedeiro | sid.inpe.br/mtc-m18@80/2008/03.17.15.17 |
|
6. Notas | |
Campos Vazios | affiliation archivingpolicy archivist callnumber contenttype copyholder copyright creatorhistory descriptionlevel dissemination documentstage doi edition group issn label lineage mark nextedition nexthigherunit notes numberofvolumes orcid parameterlist parentrepositories previousedition previouslowerunit progress project readergroup readpermission resumeid rightsholder schedulinginformation secondarydate secondarykey secondarymark serieseditor shorttitle sponsor tertiarymark tertiarytype url versiontype volume |
|