%0 Conference Proceedings
%4 sid.inpe.br/marte2/2017/10.27.14.10
%2 sid.inpe.br/marte2/2017/10.27.14.10.06
%@isbn 978-85-17-00088-1
%F 59973
%T Análise multitemporal do crescimento de áreas de mineração nos mármores da Serra de Itaoca, sul do Espírito Santo
%D 2017
%A Oliveira, Matheus Serri Moulin de,
%A Fortes, Paulo de Tarso Ferro Oliveira,
%@electronicmailaddress matheusserri@hotmail.com
%E Gherardi, Douglas Francisco Marcolino,
%E Aragão, Luiz Eduardo Oliveira e Cruz de,
%B Simpósio Brasileiro de Sensoriamento Remoto, 18 (SBSR)
%C Santos
%8 28-31 maio 2017
%I Instituto Nacional de Pesquisas Espaciais (INPE)
%J São José dos Campos
%P 5424-5431
%S Anais
%1 Instituto Nacional de Pesquisas Espaciais (INPE)
%X The development of mining in Itaoca Ridge, Cachoeiro de Itapemirim, south of Espírito Santo, Brazil, has increased considerably in last 30 years. This work has as objective the study multitemporal of mining expansion areas in this region. Were utilized images of Landsat 5, 7 e 8 satellites of 1987, 1999, 2007 and 2016 years. These images were preprocessed with clipping, contrast and afertly processed in bands compositions, segmentation and classification. Finally, the products generated in processing stage were evaluated and compared with orthophotos. The best RGB composition was RGB 421 in Landsat satellities 5 and 7, however for Landsat 8 satellite the best was RGB 532. In the segmentation technical was employed 80 and 1000 of similarity and 1 to 5 pixel area attributes, while the classification technical utilized acceptance limit of 75% or 95% and 5 iterations numbers. The results showed that the classes generated for segmentation and classification were able to distinguished mining areas to urban center, but were unable to distinguished mining areas to exposed ground zones. The increases was of almost 1000% in 30 years due the increases of exportation and Brazilian intern market development since 2000 year.
%9 Análise de séries temporais de imagens de satélite
%@language pt
%3 59973.pdf