@Article{LaRosaFeiHapSanCos:2019:CoDeLe,
author = "La Rosa, Laura Elena and Feitosa, Raul Queiroz and Happ, Patrick
Nigri and Sanches, Ieda Del'Arco and Costa, Gilson Alexandre
Ostwald Pedro",
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 {Instituto Nacional
de Pesquisas Espaciais (INPE)} and {Universidade Estadual do Rio
de Janeiro (UFRJ)}",
title = "Combining deep learning and prior knowledge for crop mapping in
tropical regions from multitemporal SAR image sequences",
journal = "Remote Sensing",
year = "2019",
volume = "11",
number = "17",
pages = "e2029",
keywords = "crop mapping, tropical agriculture, SAR, deep learning,
Sentinel-1, multitemporal image analysis.",
abstract = ": Accurate crop type identification and crop area estimation from
remote sensing data in tropical regions are still considered
challenging tasks. The more favorable weather conditions, in
comparison to the characteristic conditions of temperate regions,
permit higher flexibility in land use, planning, and management,
which implies complex crop dynamics. Moreover, the frequent cloud
cover prevents the use of optical data during large periods of the
year, making SAR data an attractive alternative for crop mapping
in tropical regions. This paper evaluates the effectiveness of
Deep Learning (DL) techniques for crop recognition from multi-date
SAR images from tropical regions. Three DL strategies are
investigated: autoencoders, convolutional neural networks, and
fully-convolutional networks. The paper further proposes a
post-classification technique to enforce prior knowledge about
crop dynamics in the target area. Experiments conducted on a
Sentinel-1 multitemporal sequence of a tropical region in Brazil
reveal the pros and cons of the tested methods. In our
experiments, the proposed crop dynamics model was able to correct
up to 16.5% of classification errors and managed to improve the
performance up to 3.2% and 8.7% in terms of overall accuracy and
average F1-score, respectively.",
doi = "10.3390/rs11172029",
url = "http://dx.doi.org/10.3390/rs11172029",
issn = "2072-4292",
language = "en",
targetfile = "remotesensing-11-02029-v2.pdf",
urlaccessdate = "27 abr. 2024"
}