| |
|
|
| Registros recuperados : 7 | |
| 2. |  | PEREIRA, P. R. M.; BOLFE, E. L.; RODRIGUES, T. C. S.; SANO, E. E. Dynamics of agricultural expansion in areas of the Brazilian savanna between 2000 and 2019. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, v. 43-3, B3, p. 1607-1614, 2020. Edition of proceedings of the 2020 edition of the XXIVth ISPRS Congres. This research is funded by the São Paulo Research Foundation (FAPESP), grant number 2019/26222-6.| Biblioteca(s): Embrapa Agricultura Digital. |
|    |
| 5. | | PEREIRA, P. R. M.; COSTA, F. W. D.; BOLFE, E. L.; MACARRINGE, L.; BOTELHO, A. C. Comparison of classification algorithms of images for the mapping of the land covering in Tasso Fragoso municipality, Brazil. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, V. V-3-2021, p. 167-173, 2021. This research is funded by the São Paulo Research Foundation (FAPESP), grant number 2019/26222-6.| Biblioteca(s): Embrapa Agricultura Digital. |
| |
| 7. | | PENHA, A. R.; BOLFE, E. L.; PEREIRA, P. R. M.; PARREIRAS, T. C.; VICTORIA, D. de C. Imagens Sentinel - 2A para mapeamento de uso e cobertura da terra em áreas de expansão agrícola no Cerrado. In: CONGRESSO INTERINSTITUCIONAL DE INICIAÇÃO CIENTÍFICA, 16., 2022, Campinas. Anais... Campinas: Instituto Agronômico, 2022. p. 1-2. Evento online. CIIC 2022. Nº 22601. Esta pesquisa é financiada pela Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP), processo n. 2019/26222-6.| Biblioteca(s): Embrapa Agricultura Digital. |
| |
| Registros recuperados : 7 | |
|
|
|
Registro Completo
|
Biblioteca(s): |
Embrapa Agricultura Digital. |
|
Data corrente: |
22/06/2021 |
|
Data da última atualização: |
03/03/2023 |
|
Tipo da produção científica: |
Artigo em Periódico Indexado |
|
Circulação/Nível: |
B - 3 |
|
Autoria: |
PEREIRA, P. R. M.; COSTA, F. W. D.; BOLFE, E. L.; MACARRINGE, L.; BOTELHO, A. C. |
|
Afiliação: |
Unicamp; Unesp; EDSON LUIS BOLFE, Unicamp, CNPTIA; Unicamp; Unicamp. |
|
Título: |
Comparison of classification algorithms of images for the mapping of the land covering in Tasso Fragoso municipality, Brazil. |
|
Ano de publicação: |
2021 |
|
Fonte/Imprenta: |
ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, V. V-3-2021, p. 167-173, 2021. |
|
DOI: |
https://doi.org/10.5194/isprs-annals-V-3-2021-167-2021 |
|
Idioma: |
Inglês |
|
Notas: |
This research is funded by the São Paulo Research Foundation (FAPESP), grant number 2019/26222-6. |
|
Conteúdo: |
Abstract. One of the main applications of satellite images is the characterization of terrestrial coverage, that from the use of classification techniques, allows the monitoring of spatial transformations of the terrestrial surface, this process being directly associated with the potential of classifiers to differentiate the most diverse data present in the images, a fundamental aspect for the use of remote sensing data. This article evaluates the performance of different classification algorithms in the mapping classes of land use and land cover in medium resolution images from the Landsat 8 program, the test area of this test corresponds to the Municipality of Tasso Fragoso (State Maranhão - Brazil), stands out for a typical vegetation cover of the Cerrado Biome, presents similar spectral patterns that induce high difficulty of class differentiation automatically. In this paper, were analyzed the machine learning algorithms C5.0 and Random Forest in comparison to traditional classification algorithms being the Minimum Distance and the Spectral Angle Mapper. The best results were generated by Random Forest with 90% accuracy and Kappa of 0.861, followed by the C5.0 algorithm. Traditional algorithms, on the other hand, presented a lower precision rate with global accuracy, not exceeding 75% of accuracy and Kappa varying between 0.507 and 0.627. The accuracy of the producer showed that all the algorithms, in major or minor tendency presented difficulties in to differentiate the areas, with rates of mistakes varying between 25 and 75%, being the main, the confusion with pastoral areas. MenosAbstract. One of the main applications of satellite images is the characterization of terrestrial coverage, that from the use of classification techniques, allows the monitoring of spatial transformations of the terrestrial surface, this process being directly associated with the potential of classifiers to differentiate the most diverse data present in the images, a fundamental aspect for the use of remote sensing data. This article evaluates the performance of different classification algorithms in the mapping classes of land use and land cover in medium resolution images from the Landsat 8 program, the test area of this test corresponds to the Municipality of Tasso Fragoso (State Maranhão - Brazil), stands out for a typical vegetation cover of the Cerrado Biome, presents similar spectral patterns that induce high difficulty of class differentiation automatically. In this paper, were analyzed the machine learning algorithms C5.0 and Random Forest in comparison to traditional classification algorithms being the Minimum Distance and the Spectral Angle Mapper. The best results were generated by Random Forest with 90% accuracy and Kappa of 0.861, followed by the C5.0 algorithm. Traditional algorithms, on the other hand, presented a lower precision rate with global accuracy, not exceeding 75% of accuracy and Kappa varying between 0.507 and 0.627. The accuracy of the producer showed that all the algorithms, in major or minor tendency presented difficulties in to differentiate th... Mostrar Tudo |
|
Palavras-Chave: |
Algoritmos de aprendizado de máquina; Bioma cerrado; Cerrado Biome; Classificação digital; Classification algorithms; Cobertura da terra; Digital Classification; Landsat 8; Machine learning algorithms; Maranhão State; Performance Indexes; Random Forest. |
|
Thesagro: |
Uso da Terra. |
|
Thesaurus NAL: |
Land cover; Land use. |
|
Categoria do assunto: |
-- |
|
URL: |
https://ainfo.cnptia.embrapa.br/digital/bitstream/item/223984/1/PL-Comparison-classification-algorithm-ISPRS-2021.pdf
|
|
Marc: |
LEADER 02934naa a2200373 a 4500
001 2132498
005 2023-03-03
008 2021 bl uuuu u00u1 u #d
024 7 $ahttps://doi.org/10.5194/isprs-annals-V-3-2021-167-2021$2DOI
100 1 $aPEREIRA, P. R. M.
245 $aComparison of classification algorithms of images for the mapping of the land covering in Tasso Fragoso municipality, Brazil.$h[electronic resource]
260 $c2021
500 $aThis research is funded by the São Paulo Research Foundation (FAPESP), grant number 2019/26222-6.
520 $aAbstract. One of the main applications of satellite images is the characterization of terrestrial coverage, that from the use of classification techniques, allows the monitoring of spatial transformations of the terrestrial surface, this process being directly associated with the potential of classifiers to differentiate the most diverse data present in the images, a fundamental aspect for the use of remote sensing data. This article evaluates the performance of different classification algorithms in the mapping classes of land use and land cover in medium resolution images from the Landsat 8 program, the test area of this test corresponds to the Municipality of Tasso Fragoso (State Maranhão - Brazil), stands out for a typical vegetation cover of the Cerrado Biome, presents similar spectral patterns that induce high difficulty of class differentiation automatically. In this paper, were analyzed the machine learning algorithms C5.0 and Random Forest in comparison to traditional classification algorithms being the Minimum Distance and the Spectral Angle Mapper. The best results were generated by Random Forest with 90% accuracy and Kappa of 0.861, followed by the C5.0 algorithm. Traditional algorithms, on the other hand, presented a lower precision rate with global accuracy, not exceeding 75% of accuracy and Kappa varying between 0.507 and 0.627. The accuracy of the producer showed that all the algorithms, in major or minor tendency presented difficulties in to differentiate the areas, with rates of mistakes varying between 25 and 75%, being the main, the confusion with pastoral areas.
650 $aLand cover
650 $aLand use
650 $aUso da Terra
653 $aAlgoritmos de aprendizado de máquina
653 $aBioma cerrado
653 $aCerrado Biome
653 $aClassificação digital
653 $aClassification algorithms
653 $aCobertura da terra
653 $aDigital Classification
653 $aLandsat 8
653 $aMachine learning algorithms
653 $aMaranhão State
653 $aPerformance Indexes
653 $aRandom Forest
700 1 $aCOSTA, F. W. D.
700 1 $aBOLFE, E. L.
700 1 $aMACARRINGE, L.
700 1 $aBOTELHO, A. C.
773 $tISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, V. V-3-2021, p. 167-173, 2021.
Download
Esconder MarcMostrar Marc Completo |
|
Registro original: |
Embrapa Agricultura Digital (CNPTIA) |
|
|
Biblioteca |
ID |
Origem |
Tipo/Formato |
Classificação |
Cutter |
Registro |
Volume |
Status |
Fechar
|
| Nenhum registro encontrado para a expressão de busca informada. |
|
|
