Open Access
19 February 2013 New method for ship detection in synthetic aperture radar imagery based on the human visual attention system
Mehdi Amoon, Ahmad Bozorgi, Gholam-ali Rezai-rad
Author Affiliations +
Abstract
We propose a new algorithm for ship detection in synthetic aperture radar (SAR) images based on the human visual attention system. The human visual attention system identifies the prominent objects in images or scenes so that these objects can be more noticeable. Since the ships in a SAR image of the ocean are prominent objects, they can easily be identified through the human visual attention system. Thus, for detection of ships in the SAR images, the present study (through its application) has modeled the human visual attention system in the detection stage. In this way, not only can the targets be precisely detected, but also the falsely detected pixels are significantly reduced. Compared to most existing algorithms in the literature, our proposed algorithm can be used for both homogeneous and nonhomogeneous images. Accordingly, its performance is independent of the image type (homogeneous or nonhomogeneous) and the computation time significantly decreases. Experimental results have shown the efficiency of the proposed algorithm for various SAR images from ERS-1, ERS-2, and ALOS PALSAR data.
CC BY: © The Authors. Published by SPIE under a Creative Commons Attribution 4.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.
Mehdi Amoon, Ahmad Bozorgi, and Gholam-ali Rezai-rad "New method for ship detection in synthetic aperture radar imagery based on the human visual attention system," Journal of Applied Remote Sensing 7(1), 071599 (19 February 2013). https://doi.org/10.1117/1.JRS.7.071599
Published: 19 February 2013
Lens.org Logo
CITATIONS
Cited by 35 scholarly publications.
Advertisement
Advertisement
KEYWORDS
Synthetic aperture radar

Detection and tracking algorithms

Visualization

Target detection

Image processing

Sensors

Visual process modeling

Back to Top