@InProceedings{AdarmeHappFeit:2019:AsEaFu,
               author = "Adarme, Mabel Ortega and Happ, Patrick Nigri and Feitosa, Raul 
                         Queiroz",
          affiliation = "{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 {Pontif{\'{\i}}cia Universidade 
                         Cat{\'o}lica do Rio de Janeiro (PUC-Rio)}",
                title = "Assessment of an early fusion CNN approach applied to the 
                         deforestation detection in the Brazilian Amazon",
            booktitle = "Anais...",
                 year = "2019",
               editor = "Gherardi, Douglas Francisco Marcolino and Sanches, Ieda DelArco 
                         and Arag{\~a}o, Luiz Eduardo Oliveira e Cruz de",
                pages = "1217--1220",
         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 = "Deep learning, deforestation, image classification, early fusion, 
                         image stacking.",
             abstract = "Deforestation is one of the main causes of biodiversity reduction, 
                         climate change among others destructive phenomena. Thus, early 
                         detection of deforestation processes is of paramount importance in 
                         the recent year. Motivated by this scenario the present work 
                         focuses on assessing a DL approach called Early Fusion (EF) for 
                         automatic deforestation detection. Change detection approaches 
                         based on Random Forest (RF) and Change Vector Analysis (CVA) were 
                         adopted as baselines for comparison purposes. These approaches 
                         were evaluated in a region located in the state of Par{\'a}, 
                         Brazil, where two images from Landsat 8 satellite were acquired to 
                         detect deforested areas from 2016 to 2017. Their corresponding 
                         references were collected from the Satellite Deforestation 
                         Monitoring Project in the Legal Amazon (PRODES). In the 
                         experiments, the EF approach outperformed RF and CVA baselines, 
                         identifying in a better way the regions that have suffered 
                         deforestation.",
  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/3U67ADP",
                  url = "http://urlib.net/ibi/8JMKD3MGP6W34M/3U67ADP",
           targetfile = "97707.pdf",
                 type = "Mudan{\c{c}}a de uso e cobertura da Terra",
        urlaccessdate = "03 maio 2024"
}