@Article{TorresTuVeFeSiMaAl:2021:DeDeFu,
author = "Torres, Daliana Lobo and Turnes, Javier Noa and Vega, Pedro Juan
Soto and Feitosa, Raul Queiroz and Silva, Daniel E. and Marcato
J{\'u}nior, Jos{\'e} and Almeida, Cl{\'a}udio Aparecido de",
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)} and
{Pontif{\'{\i}}cia Universidade Cat{\'o}lica do Rio de Janeiro
(PUC-Rio)} and {Instituto Nacional de Pesquisas Espaciais (INPE)}
and {Universidade Federal do Mato Grosso do Sul (UFMS)} and
{Instituto Nacional de Pesquisas Espaciais (INPE)}",
title = "Deforestation detection with fully convolutional networks in the
Amazon forest from Landsat-8 and Sentinel-2 images",
journal = "Remote Sensing",
year = "2021",
volume = "13",
number = "24",
pages = "e5084",
month = "Dec.",
note = "{Pr{\^e}mio CAPES Elsevier 2023 - ODS 15: Vida terrestre}",
keywords = "Amazon biome, Change detection, Deep learning, Fully convolutional
neural networks, Remote sensing, Semantic segmentation.",
abstract = "The availability of remote-sensing multisource data from
optical-based satellite sensors has created new opportunities and
challenges for forest monitoring in the Amazon Biome. In
particular, change-detection analysis has emerged in recent
decades to monitor forest-change dynamics, supporting some
Brazilian governmental initiatives such as PRODES and DETER
projects for biodiversity preservation in threatened areas. In
recent years fully convolutional network architectures have
witnessed numerous proposals adapted for the change-detection
task. This paper comprehensively explores state-of-the-art fully
convolutional networks such as U-Net, ResU-Net, SegNet,
FC-DenseNet, and two DeepLabv3+ variants on monitoring
deforestation in the Brazilian Amazon. The networks performance is
evaluated experimentally in terms of Precision, Recall, F1-score,
and computational load using satellite images with different
spatial and spectral resolution: Landsat-8 and Sentinel-2. We also
include the results of an unprecedented auditing process performed
by senior specialists to visually evaluate each deforestation
polygon derived from the network with the highest accuracy results
for both satellites. This assessment allowed estimation of the
accuracy of these networks simulating a process in nature and
faithful to the PRODES methodology. We conclude that the high
resolution of Sentinel-2 images improves the segmentation of
deforestation polygons both quantitatively (in terms of F1-score)
and qualitatively. Moreover, the study also points to the
potential of the operational use of Deep Learning (DL) mapping as
products to be consumed in PRODES.",
doi = "10.3390/rs13245084",
url = "http://dx.doi.org/10.3390/rs13245084",
issn = "2072-4292",
language = "en",
targetfile = "remotesensing-13-05084-v2.pdf",
urlaccessdate = "28 abr. 2024"
}