@Article{ReisDutrEscaSant:2020:AvInTr,
               author = "Reis, Mariane Souza and Dutra, Luciano Vieira and Escada, Maria 
                         Isabel Sobral and Sant'Anna, Sidnei Jo{\~a}o Siqueira",
          affiliation = "{Instituto Nacional de Pesquisas Espaciais (INPE)} and {Instituto 
                         Nacional de Pesquisas Espaciais (INPE)} and {Instituto Nacional de 
                         Pesquisas Espaciais (INPE)} and {Instituto Nacional de Pesquisas 
                         Espaciais (INPE)}",
                title = "Avoiding invalid transitions in land cover trajectory 
                         classification with a compound maximum a posteriori approach",
              journal = "IEEE Access",
                 year = "2020",
               volume = "8",
                pages = "98787--98799",
                month = "June",
             keywords = "Classification algorithms, land cover trajectory mapping, 
                         multi-temporal classification, remote sensing, remote 
                         monitoring.",
             abstract = "Classifying remote sensing time-series in land cover trajectories 
                         can provide essential information about ecosystems functioning and 
                         about the impacts of natural phenomena or human activities over 
                         the environment. The existing approaches commonly used for this 
                         task can present serious drawbacks, such as the possibility to 
                         derive invalid trajectories, use of complex data inputs, and 
                         several classification steps. To provide a simple method for land 
                         cover trajectory classification, we present a novel algorithm 
                         named Compound Maximum a Posteriori (CMAP) classifier. CMAP 
                         incorporates the knowledge of land cover dynamics and the 
                         information of multi-temporal data sets to produce only valid land 
                         cover trajectories using a global generative classification 
                         approach and simple inputs. CMAP was tested in two case studies, 
                         in which we compared land cover trajectories obtained by CMAP to 
                         those obtained using the traditional Maximum Likelihood (ML) 
                         classifier in a post-classification comparison approach. In the 
                         first case study, we classified 6 images from the same sensor, 
                         using the same land cover legend. In the second case study, we 
                         classified 3 images from different types of sensors, using 
                         different land cover legend levels. Because of its formulation, 
                         CMAP does not return invalid transitions/trajectories as 
                         classification results. The use of ML and post-classification 
                         comparison, on the other hand, resulted in invalid land cover 
                         trajectories in more than 50% of the used images in both case 
                         studies. Furthermore, the use of CMAP leads to better accuracy 
                         indexes for land cover classification of each date and reduces the 
                         classification noise.",
                  doi = "10.1109/ACCESS.2020.2997019",
                  url = "http://dx.doi.org/10.1109/ACCESS.2020.2997019",
                 issn = "2169-3536",
             language = "en",
           targetfile = "reis_avoiding.pdf",
        urlaccessdate = "18 abr. 2024"
}