| |
|
|
|
Registro Completo |
|
Biblioteca(s): |
Embrapa Solos. |
|
Data corrente: |
06/01/2009 |
|
Data da última atualização: |
26/10/2021 |
|
Tipo da produção científica: |
Artigo em Anais de Congresso / Nota Técnica |
|
Autoria: |
ARVOR, D.; JONATHAN, M.; MEIRELLES, M. S. P.; DUBREUIL, V. |
|
Afiliação: |
D. Arvor, Université Rennes; M. Jonathan, Université Rennes; MARGARETH GONCALVES SIMOES, CNPS; V. Dubreuil, Université Rennes. |
|
Título: |
Detecting outliers and asserting consistency in agriculture ground truth information by using temporal VI data from modis. |
|
Ano de publicação: |
2008 |
|
Fonte/Imprenta: |
International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, v. 37, pt. B7, p. 1031-1036, 2008. Edition of Proceedings of XXI ISPRS Congress, Beijing, Jul. 2008. |
|
Idioma: |
Inglês |
|
Conteúdo: |
Collecting ground truth data is an important step to be accomplished before performing a supervised classification. However, its quality depends on human, financial and time ressources. It is then important to apply a validation process to assess the reliability of the acquired data. In this study, agricultural infomation was collected in the Brazilian Amazonian State of Mato Grosso in order to map crop expansion based on MODIS EVI temporal profiles. The field work was carried out through interviews for the years 2005-2006 and 2006-2007. This work presents a methodology to validate the training data quality and determine the optimal sample to be used according to the classifier employed. The technique is based on the detection of outlier pixels for each class and is carried out by computing Mahalanobis distances for each pixel. The higher the distance, the further the pixel is from the class centre. Preliminary observations through variation coefficent validate the efficiency of the technique to detect outliers. Then, various subsamples are defined by applying different thresholds to exclude outlier pixels from the classification process. The classification results prove the robustness of the Maximum Likelihood and Spectral Angle Mapper classifiers. Indeed, those classifiers were insensitive to outlier exclusion. On the contrary, the decision tree classifier showed better results when deleting 7.5% of pixels in the training data. The technique managed to detect outliers for all classes. In this study, few outliers were present in the training data, so that the classification quality was not deeply affected by the outliers. MenosCollecting ground truth data is an important step to be accomplished before performing a supervised classification. However, its quality depends on human, financial and time ressources. It is then important to apply a validation process to assess the reliability of the acquired data. In this study, agricultural infomation was collected in the Brazilian Amazonian State of Mato Grosso in order to map crop expansion based on MODIS EVI temporal profiles. The field work was carried out through interviews for the years 2005-2006 and 2006-2007. This work presents a methodology to validate the training data quality and determine the optimal sample to be used according to the classifier employed. The technique is based on the detection of outlier pixels for each class and is carried out by computing Mahalanobis distances for each pixel. The higher the distance, the further the pixel is from the class centre. Preliminary observations through variation coefficent validate the efficiency of the technique to detect outliers. Then, various subsamples are defined by applying different thresholds to exclude outlier pixels from the classification process. The classification results prove the robustness of the Maximum Likelihood and Spectral Angle Mapper classifiers. Indeed, those classifiers were insensitive to outlier exclusion. On the contrary, the decision tree classifier showed better results when deleting 7.5% of pixels in the training data. The technique managed to detect outliers for ... Mostrar Tudo |
|
Palavras-Chave: |
Mapeamento de culturas; Processamento de imagens multitemporais. |
|
Thesagro: |
Sensoriamento Remoto; Uso da Terra. |
|
Categoria do assunto: |
P Recursos Naturais, Ciências Ambientais e da Terra |
|
URL: |
https://ainfo.cnptia.embrapa.br/digital/bitstream/item/148263/1/53.pdf
|
|
Marc: |
LEADER 02450nam a2200193 a 4500
001 1334106
005 2021-10-26
008 2008 bl uuuu u00u1 u #d
100 1 $aARVOR, D.
245 $aDetecting outliers and asserting consistency in agriculture ground truth information by using temporal VI data from modis.$h[electronic resource]
260 $aInternational Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, v. 37, pt. B7, p. 1031-1036, 2008. Edition of Proceedings of XXI ISPRS Congress, Beijing, Jul. 2008.$c2008
520 $aCollecting ground truth data is an important step to be accomplished before performing a supervised classification. However, its quality depends on human, financial and time ressources. It is then important to apply a validation process to assess the reliability of the acquired data. In this study, agricultural infomation was collected in the Brazilian Amazonian State of Mato Grosso in order to map crop expansion based on MODIS EVI temporal profiles. The field work was carried out through interviews for the years 2005-2006 and 2006-2007. This work presents a methodology to validate the training data quality and determine the optimal sample to be used according to the classifier employed. The technique is based on the detection of outlier pixels for each class and is carried out by computing Mahalanobis distances for each pixel. The higher the distance, the further the pixel is from the class centre. Preliminary observations through variation coefficent validate the efficiency of the technique to detect outliers. Then, various subsamples are defined by applying different thresholds to exclude outlier pixels from the classification process. The classification results prove the robustness of the Maximum Likelihood and Spectral Angle Mapper classifiers. Indeed, those classifiers were insensitive to outlier exclusion. On the contrary, the decision tree classifier showed better results when deleting 7.5% of pixels in the training data. The technique managed to detect outliers for all classes. In this study, few outliers were present in the training data, so that the classification quality was not deeply affected by the outliers.
650 $aSensoriamento Remoto
650 $aUso da Terra
653 $aMapeamento de culturas
653 $aProcessamento de imagens multitemporais
700 1 $aJONATHAN, M.
700 1 $aMEIRELLES, M. S. P.
700 1 $aDUBREUIL, V.
Download
Esconder MarcMostrar Marc Completo |
|
Registro original: |
Embrapa Solos (CNPS) |
|
|
Biblioteca |
ID |
Origem |
Tipo/Formato |
Classificação |
Cutter |
Registro |
Volume |
Status |
URL |
Voltar
|
|
|
| Registros recuperados : 1 | |
| 1. |  | ARVOR, D.; JONATHAN, M.; MEIRELLES, M. S. P.; DUBREUIL, V. Detecting outliers and asserting consistency in agriculture ground truth information by using temporal VI data from modis. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, v. 37, pt. B7, p. 1031-1036, 2008. Edition of Proceedings of XXI ISPRS Congress, Beijing, Jul. 2008.| Tipo: Artigo em Anais de Congresso / Nota Técnica |
| Biblioteca(s): Embrapa Solos. |
|    |
| Registros recuperados : 1 | |
|
| Nenhum registro encontrado para a expressão de busca informada. |
|
|
