Use este identificador para citar ou linkar para este item: http://repositorio.ufla.br/jspui/handle/1/13649
Título: Comparação de classificadores supervisionados na discriminação de áreas cafeeiras em Campos Gerais - Minas Gerais
Título(s) alternativo(s): Comparison of supervised classifiers in discrimination coffee areas filds in Campos Gerais - Minas Gerais
Autores: Sarmiento, Christiany Mattioli
Ramirez, Gláucia Miranda
Coltri, Priscila Pereira
Silva, Luis Felipe Lima e
Nassur, Otávio Augusto Carvalho
Soares, Jefferson Francisco
Palavras-chave: Cafeicultura
Remote sensing
Ciências Agrárias
Sensoriamento remoto
Análise de imagem orientada ao objeto
Coffee farming
Object-oriented image analyses
Data do documento: 2014
Citação: SARMIENTO, C. M. et al. Comparação de classificadores supervisionados na discriminação de áreas cafeeiras em Campos Gerais - Minas Gerais. Coffee Science, Lavras, v. 9, n. 4, p. 546-557, out./dez. 2014.
Resumo: The use of remote sensing techniques represents a significant advance for the coffee crop data, mainly to complement the currently techniques that have been used. In this context, this study aimed to map coffee areas in high resolution images using object-oriented images analyses methods, with k nearest neighbor (KNN) and support vector machine (SVM) algorithm, and pixel-by-pixel methods, using maximum likelihood (Maxver) algorithm. The study area was mapped using two classes: ‘coffee’ and ‘other uses’. We performed the mappings accuracy analysis using reference map and it was found that the pixel by pixel classification with maximum likelihood algorithm has the best results, with kappa value of 0.78 and 94.61% of accuracy. In this study, we concluded that the pixel by pixel method of Maxver algorithm seems more efficient to discriminate coffee areas when considering only two types of land use, coffee and no coffee, in high resolution images.
URI: http://repositorio.ufla.br/jspui/handle/1/13649
http://www.coffeescience.ufla.br/index.php/Coffeescience/article/view/760
Aparece nas coleções:Coffee Science



Este item está licenciada sob uma Licença Creative Commons Creative Commons