Paper
15 April 2008 Enhanced ship detection from overhead imagery
Heidi Buck, Elan Sharghi, Chessa Guilas, John Stastny, William Morgart, Brian Schalcosky, Keith Pifko
Author Affiliations +
Abstract
In the authors' previous work, a sequence of image-processing algorithms was developed that was suitable for detecting and classifying ships from panchromatic Quickbird electro-optical satellite imagery. Presented in this paper are several new algorithms, which improve the performance and enhance the capabilities of the ship detection software, as well as an overview on how land masking is performed. Specifically, this paper describes the new algorithms for enhanced detection including for the reduction of false detects such as glint and clouds. Improved cloud detection and filtering algorithms are described as well as several texture classification algorithms are used to characterize the background statistics of the ocean texture. These detection algorithms employ both cloud and glint removal techniques, which we describe. Results comparing ship detection with and without these false detect reduction algorithms are provided. These are components of a larger effort to develop a low-cost solution for detecting the presence of ships from readily-available overhead commercial imagery and comparing this information against various open-source ship-registry databases to categorize contacts for follow-on analysis.
© (2008) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Heidi Buck, Elan Sharghi, Chessa Guilas, John Stastny, William Morgart, Brian Schalcosky, and Keith Pifko "Enhanced ship detection from overhead imagery", Proc. SPIE 6945, Optics and Photonics in Global Homeland Security IV, 69450U (15 April 2008); https://doi.org/10.1117/12.792058
Lens.org Logo
CITATIONS
Cited by 20 scholarly publications.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Clouds

Detection and tracking algorithms

Image segmentation

Fourier transforms

Binary data

Image processing

Image filtering

Back to Top