@Article{OldoniSanPicPruAda:2022:GeAcAs,
author = "Oldoni, Lucas Volochen and Sanches, Ieda Del'Arco and Picoli,
Michelle Cristina Ara{\'u}jo and Prudente, Victor Hugo Rohden and
Adami, Marcos",
affiliation = "{Instituto Nacional de Pesquisas Espaciais (INPE)} and {Instituto
Nacional de Pesquisas Espaciais (INPE)} and {Universit{\'e}
Catholique de Louvain} and {Instituto Nacional de Pesquisas
Espaciais (INPE)} and {Instituto Nacional de Pesquisas Espaciais
(INPE)}",
title = "Geometric accuracy assessment and a framework for automatic
sub-pixel registration of WFI images from CBERS-4, CBERS-4A, and
Amazonia-1 satellites over Brazil",
journal = "Remote Sensing Applications: Society and Environment",
year = "2022",
volume = "28",
pages = "e100844",
month = "Nov.",
keywords = "Brazilian earth observation satellites, Multi-sensor approach,
Satellite images time series, Wide-field imager.",
abstract = "Brazil faces the challenge of conciliating food production with
natural vegetation preservation, and the government has been
investing in Earth Observation satellites to assist in this task.
In this context, images from the Wide-Field Imager (WFI) sensor
onboard the China-Brazil Earth Resources Satellite (CBERS-4),
CBERS-4A, and Amazonia-1 have been used in remote sensing
applications in Brazil. However, the geometric accuracy of the WFI
data has not yet been documented in the literature, as it was done
for other satellites/sensors such as TERRA/MODIS, Landsat-8/OLI,
and Sentinel-2/MSI. This work presents the first study to assess
the geometric accuracy of WFI images along different spectral
channels, from multi-temporal images, and taking Sentinel-2/MSI
images as a reference. Surface reflectance WFI images, Level-4
(orthorectified) with spatial resolution of 55 m (CBERS-4A) and 64
m (CBERS-4 and Amazonia-1) were analysed. Thousands of control
points (CPs) were used to quantify the geometric accuracy of more
than 300 WFI images and to construct multiple mapping functions to
correct the displacements found. The NIR band was taken as a
reference in the inter-channel (band-to-band) registration
evaluation. In this case, all tiles had an RMSE average of fewer
than 0.44 pixels. For the multi-temporal case, the CBERS-4A/WFI
had the highest average RMSE (0.87 ± 0.34 pixels). Considering the
Sentinel-2/MSI as a reference, there were observed shifts up to
1.45 pixels for CBERS-4/WFI and Amazonia-1/WFI and 2.5 pixels for
CBERS-4A/WFI. Given the displacements found, image registration is
needed for further time series analysis of WFI images for several
applications that requiring precise sub-pixel registration (i.e.,
land use cover change). As a result, we propose a framework for
the automatic registration of WFI images to properly foster the
use of WFI images. This framework substantially reduced the
misregistrations, decreasing the RMSE average to less than 0.29
pixels for the WFI images from the three satellites. The use of
the 2nd degree polynomial as a mapping function proved to be
appropriate for registering the WFI data.",
doi = "10.1016/j.rsase.2022.100844",
url = "http://dx.doi.org/10.1016/j.rsase.2022.100844",
issn = "2352-9385",
language = "en",
targetfile = "1-s2.0-S2352938522001525-main.pdf",
urlaccessdate = "02 maio 2024"
}