%0 Conference Proceedings
%4 dpi.inpe.br/marte/2011/07.22.17.30
%2 dpi.inpe.br/marte/2011/07.22.17.30.35
%@isbn 978-85-17-00056-0 (Internet)
%@isbn 978-85-17-00057-7 (DVD)
%T Análise de Vetor de Mudança para o estudo de áreas agrícolas no Cerrado
%D 2011
%A Castillo, Enrique Maurício del,
%A Epiphanio, José Carlos Neves,
%@affiliation Instituto Nacional de Pesquisas Espaciais - INPE
%@affiliation Instituto Nacional de Pesquisas Espaciais - INPE
%@electronicmailaddress castillo@dsr.inpe.br
%@electronicmailaddress epiphanio@dsr.inpe.br
%E Epiphanio, José Carlos Neves,
%E Galvão, Lênio Soares,
%B Simpósio Brasileiro de Sensoriamento Remoto, 15 (SBSR).
%C Curitiba
%8 30 abr. - 5 maio 2011
%I Instituto Nacional de Pesquisas Espaciais (INPE)
%J São José dos Campos
%P 6372-6379
%S Anais
%1 Instituto Nacional de Pesquisas Espaciais (INPE)
%K remote sensing, change detection, LSMM, PCA, spectral indices.
%X This paper intends to compare and discuss three different approaches of the change vector analysis technique (CVA) for identification of changes in land use and land cover, in an agricultural area of the Brazilian Savannah (Cerrado). The methods used involved the use of spectral indices, principal components analysis (PCA), and linear spectral mixing model (LSMM). The results showed a good potential of the three methods to identify changed and no changed pixels. Most differences were found in the direction of change image. Here, the results showed that the modifications in the change detection techniques exerted apparent influence on detection results. But most of the methods showed a relative difficulty to associate the direction of change to a specific land use/cover change. The best results were found for LSMM and PCA, while the spectral indices showed a high scene dependency and the results were not as satisfactory.
%9 Uso e Cobertura da Terra
%@language pt
%3 p0992.pdf