Vertaisarvioitu artikkeli konferenssijulkaisussa (A4)

Comparative Analysis of Image Fusion Methods in Marine Environment

Julkaisun tekijät: Fahimeh Farahnakian, Parisa Movahedi, Jussi Poikonen, Eero Lehtonen, Dimitrios Makris, Jukka Heikkonen

Konferenssin vakiintunut nimi: IEEE International Symposium on Robotic and Sensors Environments

Julkaisuvuosi: 2019

Kirjan nimi *: 2019 IEEE International Symposium on Robotic and Sensors Environments (ROSE)

ISBN: 978-1-7281-1965-6

eISBN: 978-1-7281-1964-9



Image fusion methods have gained a lot of attraction
over the past few years in the field of sensor fusion. An efficient
image fusion approach can obtain complementary information
from various multi-modality images. In addition, the fused image
is more robust to imperfect conditions such as mis-registration
and noise. The aim of this paper is to explore the performance
of existing deep learning-based and traditional image fusion
techniques for our real marine images. The performance of
these techniques is evaluated with six common quality metrics.
Image data was collected using a sensor system onboard a vessel
in the Finnish archipelago. This system is used for developing
autonomous vessels, and records data in a range of operation
and climatic conditions. To the best of our knowledge, there
is not a comparative study of RGB and infrared image fusion
algorithms evaluated in a marine environment. Experimental
results indicate that deep learning-based fusion methods can
significantly improve the image fusion performance considering
both the visual quality and objective assessment comparison
against with other methods.

Last updated on 2021-24-06 at 12:07