%0 Conference Proceedings
%4 sid.inpe.br/marte2/2017/10.27.13.09.23
%2 sid.inpe.br/marte2/2017/10.27.13.09.24
%@isbn 978-85-17-00088-1
%F 59728
%T Classificação baseada em objetos na bacia hidrográfica do rio Caceribu-RJ, e validação a partir de pontos aleatórios e imagens de alta resolução
%D 2017
%A Augusto, Rafael Cardão,
%A Costa, Evelyn de Castro Porto,
%A Seabra, Vinicius da Silva,
%@electronicmailaddress rafaelcardao@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 3399-3406
%S Anais
%1 Instituto Nacional de Pesquisas Espaciais (INPE)
%X The interpretation of satellite images allows the generation of maps, through the computational tools of geoprocessing, where it is possible to extract quantitative data on a particular topic. One of the main applications of this technology is in the characterization of human activities on the earth''s surface, and the land use and land cover an essential information for the understanding human manifestations. The aim of this study is mapping the land use and land cover of the Caceribu watershed, in the state of Rio de Janeiro, using modeling and object-based classification, followed by validation by random points using high-resolution images from Google Earth, and Global Accuracy Index, to analyze the quality of the classification. The results showed the agriculture and pasture class as the dominant in the watershed, and the materials and methods used met the objectives, reinforcing the importance of geotechnology in environmental studies. The validation indicated a good result of the classification, but indicated the limitations of classes modeling, revealing that the samples with error were particularly associated with some specific classes. The results obtained in this study may help in the future development of management plans that aim to make the environmental recovery of the watershed, and the validation results can help perform others modeling.
%9 Classificação e mineração de dados
%@language pt
%3 59728.pdf