The authors introduce a constant false alarm rate (CFAR) detection algorithm, called K-CFAR, for automatic detection of underwater objects in sonar imagery. The K-CFAR adopts the K-distribution as a statistical model of the background. An efficient closed-form estimator for the K-distribution parameters is derived by the second-order approximation of the Polygamma function without involving a numerical iterative solution. A closed-form expression for the CFAR detection threshold is obtained by exploiting the first-order Laguerre approximation of the K-distribution. Then, to increase the probability of detection, a non-CFAR refinement to the K-CFAR, based on the spatial feature of the objects, is proposed. Experimental results obtained from 270 real sonar images of diverse environments demonstrate the superiority of the proposed algorithm compared to the state-of-the-art in terms of receiver operating characteristic curves.
Bibliographical noteFunding Information:
Part of this work was funded by the NATO Science for Peace and Security Program under grant G5293.
© The Institution of Engineering and Technology 2020
ASJC Scopus subject areas
- Electrical and Electronic Engineering