@InProceedings{CamargoSanMurAlmAlm:2019:CoAsMa,
author = "Camargo, Fl{\'a}vio Fortes and Sano, Edson Eyji and Mura,
Jos{\'e} Cl{\'a}udio and Almeida, Cl{\'a}udia Maria de and
Almeida, Tati de",
affiliation = "{Universidade de Bras{\'{\i}}lia (UnB)} and {Universidade de
Bras{\'{\i}}lia (UnB)} and {Instituto Nacional de Pesquisas
Espaciais (INPE)} and {Instituto Nacional de Pesquisas Espaciais
(INPE)} and {Universidade de Bras{\'{\i}}lia (UnB)}",
title = "A comparative assessment of machine-learning techniques for land
use and land cover classification of the Brazilian tropical
savanna using ALOS-2/PALSAR-2 polarimetric images",
year = "2019",
organization = "International Geoscience and Remote Sensing Symposium (IGARSS)",
note = "Publicado na revista: Remote Sensing, v.11, 2019",
keywords = "SAR, polarimetry, data mining, thematic mapping, Cerrado.",
abstract = "This study proposes a workflow for land use and land cover (LULC)
classification of Advanced Land Observing Satellite-2 (ALOS-2)
Phased Array type L-band Synthetic Aperture Radar-2 (PALSAR-2)
images of the Brazilian tropical savanna (Cerrado) biome. The
following LULC classes were considered: forestlands; shrublands;
grasslands; reforestations; croplands; pasturelands; bare
soils/straws; urban areas; and water reservoirs. The proposed
approach combines polarimetric attributes, image segmentation, and
machine-learning procedures. A set of 125 attributes was generated
using polarimetric ALOS-2/PALSAR-2 images, including the van Zyl,
Freeman Durden, Yamaguchi, and CloudePottier target decomposition
components, incoherent polarimetric parameters (biomass indices
and polarization ratios), and HH-, HV-, VH-, and VV-polarized
amplitude images. These attributes were classified using the Naive
Bayes (NB), DT J48 (DT = decision tree), Random Forest (RF),
Multilayer Perceptron (MLP), and Support Vector Machine (SVM)
algorithms. The RF, MLP, and SVM classifiers presented the most
accurate performances. NB and DT J48 classifiers showed a lower
performance in relation to the RF, MLP, and SVM. The DT J48
classifier was the most suitable algorithm for discriminating
urban areas and natural vegetation cover. The proposed workflow
can be replicated for other SAR images with different acquisition
modes or for other types of vegetation domains.",
conference-location = "Yokohama, Japan",
conference-year = "28 July - 02 Aug.",
doi = "10.3390/rs11131600",
url = "http://dx.doi.org/10.3390/rs11131600",
language = "en",
targetfile = "remotesensing-11-01600.pdf",
urlaccessdate = "27 abr. 2024"
}