@InProceedings{DutraReisSant:2019:DeMuUt,
               author = "Dutra, Luciano Vieira and Reis, Mariane Souza and Sant'Anna, 
                         Sidnei Jo{\~a}o Siqueira",
          affiliation = "{Instituto Nacional de Pesquisas Espaciais (INPE)} and {Instituto 
                         Nacional de Pesquisas Espaciais (INPE)} and {Instituto Nacional de 
                         Pesquisas Espaciais (INPE)}",
                title = "Detec{\c{c}}{\~a}o de mudan{\c{c}}as utilizando 
                         segmenta{\c{c}}{\~o}es multidatas e dados de textura de imagens 
                         Landsat5",
            booktitle = "Anais...",
                 year = "2019",
               editor = "Gherardi, Douglas Francisco Marcolino and Sanches, Ieda DelArco 
                         and Arag{\~a}o, Luiz Eduardo Oliveira e Cruz de",
                pages = "1528--1531",
         organization = "Simp{\'o}sio Brasileiro de Sensoriamento Remoto, 19. (SBSR)",
            publisher = "Instituto Nacional de Pesquisas Espaciais (INPE)",
              address = "S{\~a}o Jos{\'e} dos Campos",
             keywords = "Sensoriamento Remoto, detec{\c{c}}{\~a}o de mudan{\c{c}}as, 
                         Landsat, RBC, OBIA, Remote Sensing, Change Detection, RBC, OBIA, 
                         Land cover mapping.",
             abstract = "O uso de dados de sensoriamento remoto permite fazer an{\'a}lises 
                         de mudan{\c{c}}as em grandes {\'a}reas, a um custo menor do que 
                         o uso extensivo de trabalho de campo. Dentre os m{\'e}todos 
                         usados para esse fim, destaca-se a an{\'a}lise das 
                         diferen{\c{c}}as que ocorrem entre classifica{\c{c}}{\~o}es 
                         baseadas em regi{\~o}es (RBC) entre datas de interesse. O 
                         objetivo desse trabalho {\'e} verificar se o uso da 
                         informa{\c{c}}{\~a}o de textura, dentro das regi{\~o}es 
                         detectadas, melhora a acur{\'a}cia das 
                         classifica{\c{c}}{\~o}es, e, por conseguinte, a 
                         detec{\c{c}}{\~a}o de mudan{\c{c}}as da superf{\'{\i}}cie 
                         terrestre. A {\'a}rea de teste {\'e} localizada nas cercanias da 
                         Floresta Nacional do Tapaj{\'o}s, no estado do Par{\'a}. Com o 
                         uso de uma metodologia abrangente e otimizante foi 
                         poss{\'{\i}}vel concluir que o uso de dados de textura 
                         tradicionais n{\~a}o melhorou o resultado final e que a pesquisa 
                         em detec{\c{c}}{\~a}o computacional de mudan{\c{c}}as deve ser 
                         ampliada para obter mais resultados satisfat{\'o}rios. ABSTRACT: 
                         Land cover change detection of large areas is executed at lower 
                         cost using remote sensing data, as opposed to the extensive use of 
                         fieldwork. One of the main methods used for this purpose is the 
                         difference analysis that occurs between two dates Region Based 
                         Classifications. The objective of this work is to verify if the 
                         use of the texture information, within the detected regions, 
                         improves the classification accuracy, and, therefore, the 
                         detection of changes of the terrestrial surface. The test area is 
                         located in the vicinity of the Tapaj{\'o}s National Forest, 
                         Par{\'a} state. Using a comprehensive and optimizing methodology, 
                         it was possible to conclude that the use of traditional texture 
                         data did not improve the final results. It was also observed that 
                         research on computational detection of land use and land cover 
                         changes must be expanded to obtain results that are more 
                         satisfactory.",
  conference-location = "Santos",
      conference-year = "14-17 abril 2019",
                 isbn = "978-85-17-00097-3",
             language = "pt",
         organisation = "Instituto Nacional de Pesquisas Espaciais (INPE)",
                  ibi = "8JMKD3MGP6W34M/3TUT3DB",
                  url = "http://urlib.net/ibi/8JMKD3MGP6W34M/3TUT3DB",
           targetfile = "97281.pdf",
                 type = "Classifica{\c{c}}{\~a}o e minera{\c{c}}{\~a}o de dados",
        urlaccessdate = "28 abr. 2024"
}