@InProceedings{NadasRodrTrinRiba:2017:AnDeCl,
               author = "Nadas, Micael Babosa and Rodrigues, Tailise Faggion and Trinca, 
                         Wladimir Alexandre and Ribas, Rodrigo Pinheiro",
                title = "An{\'a}lise do desempenho do classificador autom{\'a}tico MAXVER 
                         para uso e cobertura do solo na bacia do rio Mampituba ? SC",
            booktitle = "Anais...",
                 year = "2017",
               editor = "Gherardi, Douglas Francisco Marcolino and Arag{\~a}o, Luiz 
                         Eduardo Oliveira e Cruz de",
                pages = "4451--4458",
         organization = "Simp{\'o}sio Brasileiro de Sensoriamento Remoto, 18. (SBSR)",
            publisher = "Instituto Nacional de Pesquisas Espaciais (INPE)",
              address = "S{\~a}o Jos{\'e} dos Campos",
             abstract = "This study evaluates the thematic accuracy of the maximum 
                         likelihood classifier in a medium spatial resolution imaging 
                         satellite Landsat-8. The study area refers to the basin of the 
                         Mampituba river in Santa Catarina - Brazil. The analyzed classes 
                         were agriculture area, urban area, hydrography, exposed soil and 
                         vegetation, where we made a deeper study about the vegetal 
                         formations inside the area. The methodology consisted in first of 
                         all the discussion about the tools used in image classification 
                         such as GIS (Geographic Information System), Remote Sensing and 
                         GPS (Global Positioning System) Then, the acquisition of free 
                         Landsat 8 images, image processing, classifier training, 
                         classification, data analysis and results. The quality of the 
                         thematic map was assessed using the kappa statistic, overall 
                         accuracy, producer''s accuracies and user. The results show that 
                         automatic classification given by the classifier gives excelent 
                         results for kappa (90,09%) and overall accuracy (93,80%). Among 
                         the classes evaluated, the fragment hydrography and bare soil were 
                         those with the best accuracies and precisions. The recognition of 
                         other classes as agriculture area, urban area, vegetation, 
                         depending on the complexity of the landscape and its small 
                         dimensions in the study area, depends on the use of image 
                         interpretation techniques for further details, making it necessary 
                         a new field verification to improve and validate the results.",
  conference-location = "Santos",
      conference-year = "28-31 maio 2017",
                 isbn = "978-85-17-00088-1",
                label = "59805",
             language = "pt",
         organisation = "Instituto Nacional de Pesquisas Espaciais (INPE)",
                  ibi = "8JMKD3MGP6W34M/3PSM365",
                  url = "http://urlib.net/ibi/8JMKD3MGP6W34M/3PSM365",
           targetfile = "59805.pdf",
                 type = "Landsat OLI",
        urlaccessdate = "04 maio 2024"
}