Target detection and classification in SAR images using region covariance and co-difference

Duman, KaanEryıldırım, AbdulkadirÇetin, A. Enis2016-02-082016-02-082009-040277-786Xhttp://hdl.handle.net/11693/26739Date of Conference: 13-17 April 2009Conference name: SPIE Defense, Security, and Sensing, 2009 - Proceedings - Algorithms for Synthetic Aperture Radar Imagery XVIIn 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.EnglishAutomatic target recognition (ATR) and classificationPrincipal component analysis (PCA)Region co-difference matrixRegion covariance (RC)Synthetic aperture radar (SAR) imagesDetection accuracyDifference matrixDifference methodDistance metricsFalse alarm rateFeature parametersNew approachesObject DetectionSAR ImagesStationary targetsSynthetic aperture radar imagesTarget detectionAutomatic target recognitionCovariance matrixFeature extractionImage classificationImaging systemsObject recognitionParameter extractionPhotoacoustic effectPrincipal component analysisRadarRadar antennasRadar imagingSynthetic aperture radarSynthetic aperturesTarget dronesTarget trackingTargetsTracking radarRadar target recognitionTarget detection and classification in SAR images using region covariance and co-differenceConference Paper10.1117/12.818725