@Article{WagnerSTLFAGPA:2019:UsUnCo,
author = "Wagner, Fabien Hubert and Sanchez, Alber and Tarabalka, Yuliya and
Lotte, Rodolfo Georjute and Ferreira, Matheus Pinheiro and Aidar,
Marcos P. M. and Gloor, Emanuel and Phillips, Oliver L. and
Arag{\~a}o, Luiz Eduardo Oliveira e Cruz de",
affiliation = "{Instituto Nacional de Pesquisas Espaciais (INPE)} and {Instituto
Nacional de Pesquisas Espaciais (INPE)} and {Inria Sophia Antipo}
and {Instituto Nacional de Pesquisas Espaciais (INPE)} and
{Instituto Nacional de Pesquisas Espaciais (INPE)} and {Institute
of Botany} and {University of Leeds} and {University of Leeds} and
{Instituto Nacional de Pesquisas Espaciais (INPE)}",
title = "Using the U-net convolutional network to map forest types and
disturbance in the Atlantic rainforest with very high resolution
images",
journal = "Remote Sensing in Ecology and Conservation",
year = "2019",
volume = "2019",
pages = "1",
note = "{Pr{\^e}mio CAPES Elsevier 2023 - ODS 15: Vida terrestre}",
keywords = "Deep learning, Image segmentation, Keras, Rstudio, Tensorflow,
Tree crown delineation, Tree species detection, Vegetation type
detection, WorldView-3 image.",
abstract = "Mapping forest types and tree species at regional scales to
provide information for ecologists and forest managers is a new
challenge for the remote sensing community. Here, we assess the
potential of a U-net convolutional network, a recent deep learning
algorithm, to identify and segment (1) natural forests and
eucalyptus plantations, and (2) an indicator of forest
disturbance, the tree species Cecropia hololeuca, in very high
resolution images (0.3 m) from the WorldView-3 satellite in the
Brazilian Atlantic rainforest region. The networks for forest
types and Cecropia trees were trained with 7611 and 1568
red-greenblue (RGB) images, respectively, and their dense labeled
masks. Eighty per cent of the images were used for training and
20% for validation. The U-net network segmented forest types with
an overall accuracy >95% and an intersection over union (IoU) of
0.96. For C. hololeuca, the overall accuracy was 97% and the IoU
was 0.86. The predictions were produced over a 1600 km2 region
using WorldView-3 RGB bands pan-sharpened at 0.3 m. Natural and
eucalyptus forests compose 79 and 21% of the regions total forest
cover (82 250 ha). Cecropia crowns covered 1% of the natural
forest canopy. An index to describe the level of disturbance of
the natural forest fragments based on the spatial distribution of
Cecropia trees was developed. Our work demonstrates how a deep
learning algorithm can support applications such as vegetation,
tree species distributions and disturbance mapping on a regional
scale.",
doi = "10.1002/rse2.111",
url = "http://dx.doi.org/10.1002/rse2.111",
issn = "2056-3485",
label = "lattes: 5174466549126882 9 WagnerSTLFAGPA:2019:UsUnCo",
language = "en",
targetfile = "Wagner_et_al_Unet_2019.pdf",
urlaccessdate = "27 abr. 2024"
}