@Article{SchultzImFoSaLuAt:2015:SeSeCl,
author = "Schultz, Bruno and Immitzer, Markus and Formaggio, Ant{\^o}nio
Roberto and Sanches, Ieda Del Arco and Luiz, Alfredo Jos{\'e}
Barreto and Atzberger, Clement",
affiliation = "{Instituto Nacional de Pesquisas Espaciais (INPE)} and University
of Natural Resources and Life Sciences, Vienna (BOKU) and
{Instituto Nacional de Pesquisas Espaciais (INPE)} and {Instituto
Nacional de Pesquisas Espaciais (INPE)} and {Embrapa Meio
Ambiente} and {University of Natural Resources and Life
Sciences}",
title = "Self-guided segmentation and classification of multi-temporal
Landsat 8 images for crop type mapping in southeastern Brazil",
journal = "Remote Sensing",
year = "2015",
volume = "7",
number = "11",
pages = "14482--14508",
keywords = "OBIA, crop mapping, Brazil, multi-resolution segmentation, OLI,
random forest.",
abstract = "Only well-chosen segmentation parameters ensure optimum results of
object-based image analysis (OBIA). Manually defining suitable
parameter sets can be a time-consuming approach, not necessarily
leading to optimum results; the subjectivity of the manual
approach is also obvious. For this reason, in supervised
segmentation as proposed by Stefanski et al. (2013) one integrates
the segmentation and classification tasks. The segmentation is
optimized directly with respect to the subsequent classification.
In this contribution, we build on this work and developed a fully
autonomous workflow for supervised object-based classification,
combining image segmentation and random forest (RF)
classification. Starting from a fixed set of randomly selected and
manually interpreted training samples, suitable segmentation
parameters are automatically identified. A sub-tropical study site
located in S{\~a}o Paulo State (Brazil) was used to evaluate the
proposed approach. Two multi-temporal Landsat 8 image mosaics were
used as input (from August 2013 and January 2014) together with
training samples from field visits and VHR (RapidEye)
photo-interpretation. Using four test sites of 15 × 15 km2 with
manually interpreted crops as independent validation samples, we
demonstrate that the approach leads to robust classification
results. On these samples (pixel wise, n \≈ 1 million) an
overall accuracy (OA) of 80% could be reached while classifying
five classes: sugarcane, soybean, cassava, peanut and others. We
found that the overall accuracy obtained from the four test sites
was only marginally lower compared to the out-of-bag OA obtained
from the training samples. Amongst the five classes, sugarcane and
soybean were classified best, while cassava and peanut were often
misclassified due to similarity in the spatio-temporal feature
space and high within-class variabilities. Interestingly,
misclassified pixels were in most cases correctly identified
through the RF classification margin, which is produced as a
by-product to the classification map.",
doi = "10.3390/rs71114482",
url = "http://dx.doi.org/10.3390/rs71114482",
issn = "2072-4292",
label = "lattes: 2456184661855977 4 SchultzImFoSaLuAt:2015:SeSeCl",
language = "en",
targetfile = "1_schultz.pdf",
urlaccessdate = "27 abr. 2024"
}