@InProceedings{FerreiraCuéHapTheFei:2019:MaEuPl,
               author = "Ferreira, Matheus Pinheiro and Cu{\'e} La Rosa, Laura Elena and 
                         Happ, Patrick Nigri and Theobald, Raissa Brand and Feitosa, Raul 
                         Queroz",
          affiliation = "{Instituto Militar de Engenharia (IME)} and {Pontif{\'{\i}}cia 
                         Universidade Cat{\'o}lica do Rio de Janeiro (PUC-Rio)} and 
                         {Pontif{\'{\i}}cia Universidade Cat{\'o}lica do Rio de Janeiro 
                         (PUC-Rio)} and {Instituto Militar de Engenharia (IME)} and 
                         {Pontif{\'{\i}}cia Universidade Cat{\'o}lica do Rio de Janeiro 
                         (PUC-Rio)}",
                title = "Mapping eucalyptus plantations and natural forest areas in 
                         Landsat-TM images using deep learning",
            booktitle = "Anais...",
                 year = "2019",
               editor = "Gherardi, Douglas Francisco Marcolino and Sanches, Ieda DelArco 
                         and Arag{\~a}o, Luiz Eduardo Oliveira e Cruz de",
                pages = "2650--2653",
         organization = "Simp{\'o}sio Brasileiro de Sensoriamento Remoto, 19. (SBSR)",
            publisher = "Instituto Nacional de Pesquisas Espaciais (INPE)",
              address = "S{\~a}o Jos{\'e} dos Campos",
             keywords = "Convolutional Neural Networks, patchclassification, random forest, 
                         satellite images, tropical forests.",
             abstract = "Automatic mapping of planted and natural forests using satellite 
                         images is a challenging task due to spectral similarity issues. In 
                         this work, we assessed the use of Convolutional Neural Networks 
                         (CNNs) to discriminate between natural forest areas and eucalyptus 
                         plantations in a Landsat-TM scene. First, we produced training and 
                         testing datasets with data from the MapBiomas project. Then, CNNs 
                         were trained with input patches of different sizes (55, 77, 9 9 
                         and 11 11 pixels) to evaluate the influence of patch dimension in 
                         the classification accuracy. For comparison, pixel-wise and 
                         patch-classification were performed using the Random Forest (RF) 
                         algorithm. The best results were obtained using CNNs with 5 5 
                         patches. In this scenario, the F-score was of 97.64% for natural 
                         forests and 95.49% for eucalyptus plantations. The classification 
                         errors reached 9.06% using RF and did not exceed 3% with CNNs.",
  conference-location = "Santos",
      conference-year = "14-17 abril 2019",
                 isbn = "978-85-17-00097-3",
             language = "pt",
         organisation = "Instituto Nacional de Pesquisas Espaciais (INPE)",
                  ibi = "8JMKD3MGP6W34M/3U257BE",
                  url = "http://urlib.net/ibi/8JMKD3MGP6W34M/3U257BE",
           targetfile = "97365.pdf",
                 type = "Floresta e outros tipos de vegeta{\c{c}}{\~a}o",
        urlaccessdate = "04 maio 2024"
}