Target detection and classification in SAR images using region covariance and co-difference
Author
Duman, Kaan
Eryıldırım, Abdulkadir
Çetin, A. Enis
Date
2009-04Source Title
Proceedings of SPIE - Algorithms for Synthetic Aperture Radar Imagery XVI
Print ISSN
0277-786X
Publisher
SPIE
Language
English
Type
Conference PaperItem Usage Stats
206
views
views
136
downloads
downloads
Abstract
In this paper, a novel descriptive feature parameter extraction method from synthetic aperture radar (SAR) images is proposed. The new approach is based on region covariance (RC) method which involves the computation of a covariance matrix whose entries are used in target detection and classification. In addition the region co-difference matrix is also introduced. Experimental results of object detection in MSTAR (moving and stationary target recognition) database are presented. The RC and region co-difference method delivers high detection accuracy and low false alarm rates. It is also experimentally observed that these methods produce better results than the commonly used principal component analysis (PCA) method when they are used with different distance metrics introduced. © 2009 SPIE.
Keywords
Automatic target recognition (ATR) and classificationPrincipal component analysis (PCA)
Region co-difference matrix
Region covariance (RC)
Synthetic aperture radar (SAR) images
Detection accuracy
Difference matrix
Difference method
Distance metrics
False alarm rate
Feature parameters
New approaches
Object Detection
SAR Images
Stationary targets
Synthetic aperture radar images
Target detection
Automatic target recognition
Covariance matrix
Feature extraction
Image classification
Imaging systems
Object recognition
Parameter extraction
Photoacoustic effect
Principal component analysis
Radar
Radar antennas
Radar imaging
Synthetic aperture radar
Synthetic apertures
Target drones
Target tracking
Targets
Tracking radar
Radar target recognition
Permalink
http://hdl.handle.net/11693/26739Published Version (Please cite this version)
http://dx.doi.org/10.1117/12.818725Collections
Related items
Showing items related by title, author, creator and subject.
-
Pulse doppler radar target recognition using a two-stage SVM procedure
Eryildirim, A.; Onaran, I. (IEEE, 2010-07-07)It is possible to detect and classify moving and stationary targets using ground surveillance pulse-Doppler radars (PDRs). A two-stage support vector machine (SVM) based target classification scheme is described here. The ... -
Target detection in SAR images using codifference and directional filters
Duman, Kaan; Çetin, A. Enis (SPIE, 2010)Target detection in SAR images using region covariance (RC) and codifference methods is shown to be accurate despite the high computational cost. The proposed method uses directional filters in order to decrease the search ... -
Range-doppler radar target detection using denoising within the compressive sensing framework
Sevimli, R. Akın; Tofighi, Mohammad; Çetin, A. Enis (IEEE, 2014-09)Compressive sensing (CS) idea enables the reconstruction of a sparse signal from a small set of measurements. CS approach has applications in many practical areas. One of the areas is radar systems. In this article, the ...