%0 Journal Article
%T 基于目标区域特性的海面小目标检测快速算法
%A 邹玉兰
%A 汪国有
%A 张磊
%J 自动化学报
%P 427-433
%D 2005
%X ？Afastobjectdetectionmethodbasedonobjectregiondissimilarityand1-DAGADM(onedimensionalaveragegrayabsolutedifferencemaximum)betweenobjectandbackgroundisproposedforreal-timedefectionofsmalloffshoretargets.Thencomputationalcomplexity,antinoiseperformance,thesignal-to-noiseratio(SNR)gainbetweenoriginalimagesandtheirresultsasafunctionofSNRoforiginalimagesandreceiveroperatingcharacteristic(ROC)curveareanalyzedandcomparedwiththoseexistingmethodsofsmalltargetdetectionsuchastwodimensionalaveragegrayabsolutedifferencemaximum(2-DAGADM),mediancontrastfilteralgorithmandmulti-levelfilteralgorithm.ExperimentalresultsandtheoreticalanalysishaveshownthattheproposedmethodhasfasterspeedandmoreadaptabilitytosmallobjectshapeandalsoyieldsimprovedSNRperformance.
%K Smalltargetdetection
%K averagegrayabsolutedifferencemaximum
%K computationalcomplexity
%K signal-to-noiseratio(SNR)
%K ROCcurve
%U http://www.aas.net.cn/CN/abstract/abstract15875.shtml