@InProceedings{DuftPicScaHerGal:2015:CoDeÍn,
               author = "Duft, Daniel Garbellini and Picoli, Michelle Cristina Araujo and 
                         Scarpare, F{\'a}bio Valle and Hernandes, Thayse Aparecida Dourado 
                         and Galdos, Marcelo Valadares",
                title = "Compara{\c{c}}{\~a}o do desempenho de {\'{\i}}ndices de 
                         vegeta{\c{c}}{\~a}o do sensor MODIS para mapeamento 
                         sistem{\'a}tico da cana-de-a{\c{c}}{\'u}car",
            booktitle = "Anais...",
                 year = "2015",
               editor = "Gherardi, Douglas Francisco Marcolino and Arag{\~a}o, Luiz 
                         Eduardo Oliveira e Cruz de",
                pages = "2727--2734",
         organization = "Simp{\'o}sio Brasileiro de Sensoriamento Remoto, 17. (SBSR)",
            publisher = "Instituto Nacional de Pesquisas Espaciais (INPE)",
              address = "S{\~a}o Jos{\'e} dos Campos",
             abstract = "Currently, Brazilian sugarcane monitoring is done by official 
                         agencies (Brazilian Institute of Geography and Statistics (IBGE), 
                         Ministry of Agriculture (MAPA), National Supply Company (Conab)) 
                         through agricultural statistics. As sugarcane is produced in large 
                         areas in Brazil, it is evident the need of creating new mapping 
                         methods especially new methodologies for satellite imagery 
                         classification. Nowadays the only mapping project that exists is 
                         Canasat Project, but it is an expensive and slow method of work. 
                         Therefore, some authors developed an automated methodology for 
                         mapping cultures using the maximum and minimum values of NDVI 
                         (Normalized Difference Vegetation Index) and EVI (Enhanced 
                         Vegetation Index) satellite images obtained by Terra and SPOT 
                         platforms. Thus, this paper aims to test a methodology for 
                         automating sugarcane mapping using two indices: NDVI (Normalized 
                         Difference Vegetation Index) and EVI (Enhanced Vegetation Index), 
                         from MODIS sensor, in Paranaiba basin to identify which index have 
                         the best performance in that area and could be replicated along 
                         the years. The results showed that for 2009/10 crop season, the 
                         EVI index had a better performance than NDVI and it could be 
                         explained by NDVI saturation problem. The authors observed that 
                         the proposed method was highly efficient and fast so it could be 
                         used for sugarcane mapping.",
  conference-location = "Jo{\~a}o Pessoa",
      conference-year = "25-29 abr. 2015",
                 isbn = "978-85-17-0076-8",
                label = "542",
             language = "pt",
         organisation = "Instituto Nacional de Pesquisas Espaciais (INPE)",
                  ibi = "8JMKD3MGP6W34M/3JM4AB6",
                  url = "http://urlib.net/ibi/8JMKD3MGP6W34M/3JM4AB6",
           targetfile = "p0542.pdf",
                 type = "An{\'a}lise de s{\'e}ries de tempo de imagens de sat{\'e}lite",
        urlaccessdate = "10 maio 2024"
}