12 September 2003 Azimuth correlation models for radar imaging
Author Affiliations +
Many applications which process radar data, including automatic target recognition and synthetic aperture radar image formation, are based on probabilistic models for the raw or processed data. Often, data collected from distinct directions are assumed to represent independent observations. This assumption is not valid for all data collection scenarios. A range of models can be developed that allow for successively more complex dependencies between measured data, up to deterministic computational electromagnetic models, in which observations from different orientations have a known relationship. We consider models for the autocovariance functions of nonstationary processes defined on a circular domain that fall between these two extremes. We adopt a model of covariance as a linear combination of periodic basis functions and address maximum-likelihood estimation of the coefficients by the method of expectation-maximization (EM). Finally, we apply these estimation methods to SAR image data and demonstrate the results as they apply to target recognition.
© (2003) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Michael D. DeVore, Joseph A. O'Sullivan, Lee J. Montagnino, "Azimuth correlation models for radar imaging", Proc. SPIE 5095, Algorithms for Synthetic Aperture Radar Imagery X, (12 September 2003); doi: 10.1117/12.488642; https://doi.org/10.1117/12.488642


Recognizing occluded MSTAR targets
Proceedings of SPIE (August 24 2000)
RBI-EMML signal separation for imaging techniques
Proceedings of SPIE (August 02 2002)
The processing of the radar images for the purpose of...
Proceedings of SPIE (January 11 2007)
Time series modeling for automatic target recognition
Proceedings of SPIE (May 02 2012)

Back to Top