Affiliations: [a] Department of Cultural Technology and Communication, University of the Aegean, Mytilene, Greece | [b] Institute of Environment and Sustainability, Joint European Research Center, European Commission, Via Enrico Fermi, Italy | [c] Department of Marine Sciences, University of the Aegean, Mytilene, Greece
Correspondence:
[*]
Corresponding author: George E. Tsekouras, Department of Cultural Technology and Communication, University of the Aegean, Mytilene 81100, Greece. E-mail:[email protected]
Abstract: This paper investigates the potential of using a
polynomial radial basis function (RBF) neural network to extract the
shoreline position from coastal video images. The basic structure of the
proposed network encompasses a standard RBF network module, a module of
nodes that use Chebyshev polynomials as activation functions, and an
inference module. The experimental setup is an operational coastal video
monitoring system deployed in two sites in Southern Europe to generate
variance coastal images. The histogram of each image is approximated by
non-linear regression, and associated with a manually extracted intensity
threshold value that quantifies the shoreline position. The key idea is to
use the set of the resulting regression parameters as input data, and the
intensity threshold values as output data of the network. In summary, the
data set is extracted by quantifying the qualitative image information, and
the proposed network takes the advantage of the powerful approximation
capabilities of the Chebyshev polynomials by utilizing a small number of
coefficients. For comparative reasons, we apply a polynomial RBF network
trained by fuzzy clustering, and a feed-forward neural network trained by
the back propagation algorithm. The comparison criteria used are the
standard mean square error; the data return rates, and the root mean square
error of the cross-shore shoreline position, calculated against the
shorelines extracted by the aforementioned annotated threshold values. The
main conclusions of the simulation study are: (a) the proposed method
outperforms the other networks, especially in extracting the shoreline from
images used as testing data; (b) for higher polynomial orders it obtains
data return rates greater than 84%, and the root mean square error of the
cross-shore shoreline position is less than 1.8 meters.
