Abstract
Most integrated target detection and tracking systems employ state space models to keep track of an explicit number of individual targets.Recently,anon-state-spaceframeworkwasdevelopedforenhancingtargetde-tectioninvideobyapplyingprobabilisticmotionmodelstothesoftinformationincorrelationoutputsbeforethresholding.Thisframeworkhasbeenreferredtoasmulti-framecorrelationfiltering(MFCF),andbecauseitavoidstheuseofstate-spacemodelsandtheformationofexplicittracks,theframeworkiswell-suitedforhan-dlingsceneswithunknownnumbersoftargetsatunknownpositions.Inthispaper,weproposetousequadraticcorrelationfilters(QCFs)intheMFCFframeworkforrobusttargetdetection.Wetestourdetectionalgorithmonrealandsynthesizedsingle-targetandmulti-targetvideosequences.SimulationresultsshowthatMFCFcansignificantlyreduce(tozerointhebestcase)thefalsealarmratesofQCFsatdetectionratesabove95%inthepresenceoflargeamountsofuncorrelatednoise.WealsoshowthatMFCFismoreadeptatrejectingthosefalsepeaksduetouncorrelatednoiseratherthanthoseduetoclutterandcompressionnoise;consequently,weshowthatfiltersusedintheframeworkshouldbemadetofavorclutterrejectionovernoisetolerance.