An Expectation-Maximization Approach Applied to Underwater Target Detection (CROSBI ID 599350)
Prilog sa skupa u zborniku | izvorni znanstveni rad | međunarodna recenzija
Podaci o odgovornosti
Tai Fei ; Dieter Kraus ; Ivan Aleksi
engleski
An Expectation-Maximization Approach Applied to Underwater Target Detection
In this paper, an expectation-maximization (EM) approach assisted by Dempster-Shafer evidence theory (DST) for image segmentation is presented. The likelihood function for EM approach proposed by Sanjay-Gopal et al., which decouples the spatial correlation between pixels far away from each other, is taken into account. The Gaussian mixture model is extended to a generalized mixture model which adopts the Pearson distribution system, so that our approach can approximate the statistics of the sonar imagery with more flexibility. Moreover, an intermediate step (I-step) based on DST is introduced between the E- and M-steps of the EM to consider the spatial dependency among neighboring pixels. Finally, numerical tests are carried out on SAS images. Our approach is quantitatively compared to those methods from the literature with the help of se veral evaluation measures for image egmentation.
image segmentation; Pearson distribution system; Dempster-Shafer evidence theory; expectationmaximization algorithm; synthetic aperture sonar
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o prilogu
2014.
objavljeno
Podaci o matičnoj publikaciji
Proceedings of the International Conference on Detection and Classification of Underwater Targets (DCUT), Brest, 2012.
Isabelle Quidu, Vincent Myers, Benoit Zerr
Newcastle: Cambridge Scholars Publishing
978-1-4438-5709-3
Podaci o skupu
Nepoznat skup
predavanje
29.02.1904-29.02.2096