%0 Conference Proceedings
%4 sid.inpe.br/marte2/2017/10.27.15.52.14
%2 sid.inpe.br/marte2/2017/10.27.15.52.15
%@isbn 978-85-17-00088-1
%F 60215
%T Análise da eficiência dos índices Built-up e NDBI para classificação de áreas urbanas em imagens Landsat 8 OLI
%D 2017
%A Costa, Evelyn de Castro Porto,
%A Augusto, Rafael Cardão,
%A Seabra, Vinicius da Silva,
%@electronicmailaddress evelynportocosta@yahoo.com.br
%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 6632-6639
%S Anais
%1 Instituto Nacional de Pesquisas Espaciais (INPE)
%X The classification of images in an automated way has difficulties that can affect in the reliability of the mapping results. To solve these limitations, there are software and methodologies that allow the application of different parameters to perform image classification, such as algorithmic compositions between bands, resulting in an image that detects vegetation, water or urban areas, facilitating the classification. The urban areas are seen as more complex areas to be classified, especially in large urban áreas or with diversity of urban classes. To give subsidies to the mappings of the occupied areas, it is fundamental to test the efficiency of applying these indices and to discuss the limitations encountered. In this study, we adopted as a methodology to the comparison between a classification using NDBI and Built-Up, and a validated map, in the same study area, obtaining as results the comparison between the most underestimated and overestimated classes by the indicators. Even with some limitations in some classes, the indices presented expressive efficiencies in their performances.
%9 Urbanização
%@language pt
%3 60215.pdf