Clutter Reduction Based on Principal Component Analysis Technique for Hidden Objects Detection
Abstract
This paper brings a brief overview of the statistical method called Principal Component Analysis (PCA). It is used for clutter reduction in detection of hidden objects, targets hidden behind walls, buried landmines, etc. Since the measured data, imaged in time domain, suffer from the hyperbolic character of objects’ reflections, utilization of the Synthetic Aperture Radar (SAR) method is briefly described. Besides, the mathematical basics of PCA as well as its comparison with Singular Value Decomposition are presented. The principles of ground and clutter subtraction from image are then demonstrated using training data set and SAR processed measured data.
Keywords
Synthetic Aperture Radar, through-wall imaging, Singular Value Decomposition, Principal Component AnalysisPersistent identifier
http://hdl.handle.net/11012/37067Document type
Peer reviewedDocument version
Final PDFSource
Radioengineering. 2012, vol. 21, č. 1, s. 464-470. ISSN 1210-2512http://www.radioeng.cz/fulltexts/2012/12_01_0464_0470.pdf
Collections
- 2012/1 [71]