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/3BT2AF2 |
Repositório | sid.inpe.br/mtc-m18/2012/05.15.13.21 |
Última Atualização | 2012:05.15.13.21.48 (UTC) administrator |
Repositório de Metadados | sid.inpe.br/mtc-m18/2012/05.15.13.21.48 |
Última Atualização dos Metadados | 2018:06.04.03.55.36 (UTC) administrator |
ISBN | 978-85-17-00059-1 |
Chave de Citação | NitzeSchuAsch:2012:CoMaLe |
Título | Comparison of machine learning algorithms Random Forest, Artificial Neural Network and Support Vector Machine to Maximum Likelihood for supervised crop type classification |
Formato | On-line. |
Ano | 2012 |
Data de Acesso | 20 maio 2024 |
Tipo Secundário | PRE CI |
Número de Arquivos | 1 |
Tamanho | 698 KiB |
|
2. Contextualização | |
Autor | 1 Nitze, Ingmar 2 Schulthess, Urs 3 Asche, Hartmut |
Endereço de e-Mail do Autor | 1 ingmarnitze@gmail.com 2 uschulthess@4dmaps.de 3 gislab@uni-potsdam.de |
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 | 35-40 |
Título do Livro | Proceedings |
Organização | Instituto Nacional de Pesquisas Espaciais (INPE) |
Histórico (UTC) | 2012-05-15 13:21:48 :: wanderf@dsr.inpe.br -> administrator :: 2012-05-30 13:42:27 :: administrator -> wanderf@dsr.inpe.br :: 2012 2012-06-01 15:12:42 :: wanderf@dsr.inpe.br -> marciana :: 2012 2012-06-12 14:28:23 :: marciana -> seki@dsr.inpe.br :: 2012 2012-06-13 15:55:29 :: seki@dsr.inpe.br -> marciana :: 2012 2012-06-14 15:03:55 :: marciana -> administrator :: 2012 2018-06-04 03:55:36 :: administrator -> :: 2012 |
|
3. Conteúdo e estrutura | |
É a matriz ou uma cópia? | é a matriz |
Estágio do Conteúdo | concluido |
Transferível | 1 |
Palavras-Chave | Crop Classification Machine Learning Algorithms Support Vector Machine RapidEye |
Resumo | The classification and recognition of agricultural crop types is an important application of remote sensing. New machine learning algorithms have emerged in the last years, but so far, few studies only have compared their performance and usability. Therefore, we compared three different state-of-the-art machine learning classifiers, namely Support Vector Machine (SVM), Artificial Neural Network (ANN) and Random Forest (RF) as well as the traditional classification method Maximum Likelihood (ML) among each other. For this purpose we classified a dataset of more than 500 crop fields located in the Canadian Prairies with a stratified randomized sampling approach. Up to four multi-spectral RapidEye images from the 2009 growing season were used. We compared the mean overall classification accuracies as well as standard deviations. Furthermore, the classification accuracy of single crops was analysed. Support Vector Machine classifiers using radial basis function or polynomial kernels exhibited superior results to ANN and RF in terms of overall accuracy and robustness, while ML exhibited inferior accuracies and higher variability. Grassland exhibited the best results for early-season mono-temporal analysis. With a multi-temporal approach, the highest accuracies were achieved for Rapeseed and Field Peas. Other crops, such as Wheat, Flax and Lentils were also successfully classified. The users and producers accuracies were higher than 85 %. |
Área | SRE |
Tipo | Classification |
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/3BT2AF2 |
URL dos dados zipados | http://urlib.net/zip/8JMKD3MGP8W/3BT2AF2 |
Idioma | en |
Arquivo Alvo | 015.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 |
|