%0 Conference Proceedings
%4 sid.inpe.br/mtc-m16c/2017/12.01.20.32
%2 sid.inpe.br/mtc-m16c/2017/12.01.20.32.04
%@issn 2179-4820
%T Classificação semiautomática de áreas queimadas com o uso de redes neurais
%D 2017
%A Andrade, Ronaldo Nelis de,
%A Bittencourt, Olga,
%A Morelli, Fabiano,
%A Santos, Rafael,
%@affiliation Instituto Nacional de Pesquisas Espaciais (INPE)
%@affiliation Instituto Nacional de Pesquisas Espaciais (INPE)
%@affiliation Instituto Nacional de Pesquisas Espaciais (INPE)
%@affiliation Instituto Nacional de Pesquisas Espaciais (INPE)
%E Davis Jr., Clodoveu A. (UFMG),
%E Queiroz, Gilberto R. de (INPE),
%B Simpósio Brasileiro de Geoinformática, 18 (GEOINFO)
%C Salvador
%8 04-06 dez. 2017
%I Instituto Nacional de Pesquisas Espaciais (INPE)
%J São José dos Campos
%P 92-97
%S Anais
%X This paper presents an approach to improve the semi-automatic detection of burned areas through the use of neural networks. The approach is validated over a selected study area in the Brazilian Cerrado against reference data derived from data classified by experts. Methods are still being developed and improved, and initial results corroborate the validity of the approach, which will be extended to other study areas.
%@language pt
%3 10andrade_santos.pdf