@Article{NegriFreSilMenDut:2019:ReClPo,
author = "Negri, Rog{\'e}rio Galante and Frery, Alejandro C. and Silva,
Wagner B. and Mendes, Tatiana Sussel Gon{\c{c}}alves and Dutra,
Luciano Vieira",
affiliation = "{Universidade Estadual Paulista (UNESP)} and {Universidade Federal
de Alagoas (UFAL)} and {Instituto Militar de Engenharia (IME)} and
{Universidade Estadual Paulista (UNESP)} and {Instituto Nacional
de Pesquisas Espaciais (INPE)}",
title = "Region-based classification of PolSAR data using radial basis
kernel functions with stochastic distances",
journal = "International Journal of Digital Earth",
year = "2019",
volume = "12",
number = "6",
pages = "699--719",
month = "June",
keywords = "PolSAR, image classification, stochastic distance, minimum
distance classifier, SVM.",
abstract = "Region-based classification of PolSAR data can be effectively
performed by seeking for the assignment that minimizes a distance
between prototypes and segments. Silva et al. [Classification of
segments in PolSAR imagery by minimum stochastic distances between
wishart distributions. IEEE Journal of Selected Topics in Applied
Earth Observations and Remote Sensing 6 (3): 12631273] used
stochastic distances between complex multivariate Wishart models
which, differently from other measures, are computationally
tractable. In this work we assess the robustness of such approach
with respect to errors in the training stage, and propose an
extension that alleviates such problems. We introduce robustness
in the process by incorporating a combination of radial basis
kernel functions and stochastic distances with Support Vector
Machines (SVM). We consider several stochastic distances between
Wishart: Bhatacharyya, Kullback-Leibler, Chi-Square, R{\'e}nyi,
and Hellinger. We perform two case studies with PolSAR images,
both simulated and from actual sensors, and different
classification scenarios to compare the performance of Minimum
Distance and SVM classification frameworks. With this, we model
the situation of imperfect training samples. We show that SVM with
the proposed kernel functions achieves better performance with
respect to Minimum Distance, at the expense of more computational
resources and the need of parameter tuning. Code and data are
provided for reproducibility.",
doi = "10.1080/17538947.2018.1474958",
url = "http://dx.doi.org/10.1080/17538947.2018.1474958",
issn = "1753-8947",
label = "self-archiving-INPE-MCTIC-GOV-BR",
language = "en",
targetfile = "Region based classification of PolSAR data using radial basis
kernel functions with stochastic distances.pdf",
urlaccessdate = "26 abr. 2024"
}