@Article{XaudEpip:2014:DiUsCo,
               author = "Xaud, Maristela Ramalho and Epiphanio, Jos{\'e} Carlos Neves",
          affiliation = "{Empresa Brasileira de Pesquisa Agropecu{\'a}ria – Embrapa 
                         Roraima} and {Instituto Nacional de Pesquisas Espaciais (INPE)}",
                title = "Din{\^a}mica do uso e cobertura da terra no sudeste de Roraima 
                         utilizando t{\'e}cnicas de detec{\c{c}}{\~a}o de 
                         mudan{\c{c}}as / Land use and land cover dynamics in the 
                         southeastern Roraima using change detection techniques",
              journal = "Acta Amazonica",
                 year = "2014",
               volume = "44",
               number = "1",
                pages = "107--120",
                month = "Mar.",
             keywords = "uso da terra, detec{\c{c}}{\~a}o de mudan{\c{c}}a, 
                         imagens-fra{\c{c}}{\~a}o, sensoriamento remoto, Amaz{\^o}nia, 
                         land use, change detection, fraction images, remote sensing, 
                         Amazon.",
             abstract = "A ocupa{\c{c}}{\~a}o e consolida{\c{c}}{\~a}o do 
                         territ{\'o}rio na Amaz{\^o}nia apresentam diferentes 
                         caracter{\'{\i}}sticas relacionadas {\`a} din{\^a}mica das 
                         convers{\~o}es de uso e cobertura da terra, que podem ser 
                         analisadas utilizando imagens orbitais de sensoriamento remoto. O 
                         objetivo do presente trabalho foi avaliar os produtos de 
                         detec{\c{c}}{\~a}o de mudan{\c{c}}as gerados por an{\'a}lise 
                         de vetor de mudan{\c{c}}a (AVM) e subtra{\c{c}}{\~a}o de 
                         imagens, a partir de imagens-fra{\c{c}}{\~a}o derivadas das 
                         imagens {\'o}pticas TM/Landsat, para o estudo das convers{\~o}es 
                         de uso e cobertura da terra presentes em {\'a}rea de 
                         coloniza{\c{c}}{\~a}o agr{\'{\i}}cola na regi{\~a}o sudeste 
                         de Roraima. Analisaram-se as imagens de mudan{\c{c}}a 
                         provenientes da aplica{\c{c}}{\~a}o do AVM (magnitude, alfa e 
                         beta) e da subtra{\c{c}}{\~a}o das imagens-fra{\c{c}}{\~a}o 
                         (solo, sombra e vegeta{\c{c}}{\~a}o) quanto {\`a} sua 
                         capacidade de identificar e discriminar as convers{\~o}es 
                         existentes, de acordo com levantamento de campo. Foram testados 
                         dois algoritmos de classifica{\c{c}}{\~a}o de imagens do tipo 
                         supervisionado, Bhattacharyya e Support Vector Machine. Foram 
                         feitos agrupamentos para otimizar a identifica{\c{c}}{\~a}o das 
                         convers{\~o}es nas classifica{\c{c}}{\~o}es testadas. Houve 
                         melhor desempenho do classificador por regi{\~o}es Bhattacharyya 
                         na discrimina{\c{c}}{\~a}o das convers{\~o}es. A 
                         utiliza{\c{c}}{\~a}o das imagens-diferen{\c{c}}a das 
                         fra{\c{c}}{\~o}es como informa{\c{c}}{\~a}o de entrada para o 
                         classificador apresentou qualidade de classifica{\c{c}}{\~a}o 
                         muito boa ou excelente, sendo superior {\`a}s 
                         classifica{\c{c}}{\~o}es utilizando os produtos AVM, 
                         isoladamente ou em conjunto com as imagens-diferen{\c{c}}a. 
                         ABSTRACT: Territory occupation and consolidation in the Amazon 
                         region have some specific characteristics related to the dynamics 
                         of land use and land cover conversions, which can be analyzed 
                         using orbital remote sensing images. The aim of this study was to 
                         evaluate change detection products generated by change vector 
                         analysis (AVM) and image subtraction techniques derived from 
                         linear spectral mixing modeling (MLME), applied to Thematic 
                         Mapper/Landsat optical images, to study land use and land cover 
                         conversions occurring in agricultural settlement areas in the 
                         southeastern region of Roraima, Brazil. We analyzed change images 
                         derived from application of AVM (magnitude, alpha and beta) and 
                         subtraction of fraction images (soil, vegetation and shade), for 
                         their ability to identify and discriminate the existing 
                         conversions. An extensive field work was used as a guide to define 
                         the classes. Exploratory analyses of class behaviors were made and 
                         two supervised algorithms for image classification - Bhattacharyya 
                         and Support Vector Machine - were tested. By grouping (clumping 
                         classes), we sought to optimize conversion identification in the 
                         classification products. The results indicated better 
                         Bhattacharyya region classifier performance of conversion 
                         discrimination. The use of MLME fractions difference images as 
                         input into the classifier resulted a very good or excellent 
                         classification quality, which was better in comparison with 
                         products using AVM images, either in isolation or in conjunction 
                         with MLME difference images.",
                  doi = "10.1590/S0044-59672014000100011",
                  url = "http://dx.doi.org/10.1590/S0044-59672014000100011",
                 issn = "0044-5967",
                label = "isi 2014-05 XaudNeve:2014:LaUsLa",
             language = "pt",
           targetfile = "11.pdf",
        urlaccessdate = "03 maio 2024"
}