@Article{WagnerSiTaSeThHi:2020:UnInSe,
author = "Wagner, Fabien Hubert and Silva, Ricardo Dal Agnol da and
Tarabalka, Yuliya and Segantine, Tassiana Y. F. and Thom{\'e},
Rog{\'e}rio and Hirye, Mayumi C. M.",
affiliation = "{Instituto Nacional de Pesquisas Espaciais (INPE)} and {Instituto
Nacional de Pesquisas Espaciais (INPE)} and {Luxcarta Technology}
and Funda{\c{c}}{\~a}o de Ci{\^e}ncia, Aplica{\c{c}}{\~o}es e
Tecnologia Espaciais (FUNCATE) and Funda{\c{c}}{\~a}o de
Ci{\^e}ncia, Aplica{\c{c}}{\~o}es e Tecnologia Espaciais
(FUNCATE) and {Universidade de S{\~a}o Paulo (USP)}",
title = "U-net-id, an instance segmentation model for building extraction
from satellite images-Case study in the Joanopolis City, Brazil",
journal = "Remote Sensing",
year = "2020",
volume = "12",
number = "10",
pages = "e1544",
month = "May",
keywords = "instance segmentation, U-net, building detection, urban
landscape.",
abstract = "Currently, there exists a growing demand for individual building
mapping in regions of rapid urban growth in less-developed
countries. Most existing methods can segment buildings but cannot
discriminate adjacent buildings. Here, we present a new
convolutional neural network architecture (CNN) called U-net-id
that performs building instance segmentation. The proposed network
is trained with WorldView-3 satellite RGB images (0.3 m) and three
different labeled masks. The first is the building mask; the
second is the border mask, which is the border of the building
segment with 4 pixels added outside and 3 pixels inside; and the
third is the inner segment mask, which is the segment of the
building diminished by 2 pixels. The architecture consists of
three parallel paths, one for each mask, all starting with a U-net
model. To accurately capture the overlap between the masks, all
activation layers of the U-nets are copied and concatenated on
each path and sent to two additional convolutional layers before
the output activation layers. The method was tested with a dataset
of 7563 manually delineated individual buildings of the city of
Joan{\'o}polis-SP, Brazil. On this dataset, the semantic
segmentation showed an overall accuracy of 97.67% and an F1-Score
of 0.937 and the building individual instance segmentation showed
good performance with a mean intersection over union (IoU) of
0.582 (median IoU = 0.694).",
doi = "10.3390/rs12101544",
url = "http://dx.doi.org/10.3390/rs12101544",
issn = "2072-4292",
language = "en",
targetfile = "remotesensing-12-01544-v2.pdf",
urlaccessdate = "11 maio 2024"
}