Comments on Cram r–Rao lower bound for tracking multiple targets.pdf

Comments on Cram r–Rao lower bound for tracking multiple targets.pdf

ID:34747286

大小:175.01 KB

页数:3页

时间:2019-03-10

Comments on Cram r–Rao lower bound for tracking multiple targets.pdf_第1页
Comments on Cram r–Rao lower bound for tracking multiple targets.pdf_第2页
Comments on Cram r–Rao lower bound for tracking multiple targets.pdf_第3页
资源描述:

《Comments on Cram r–Rao lower bound for tracking multiple targets.pdf》由会员上传分享,免费在线阅读,更多相关内容在学术论文-天天文库

1、CommentsonCrame´rRaolowerboundfortrackingmultipletargetsB.RisticandM.MorelandeAbstract:Inarecentpaper,Risticetal.,2004,proposedasimpleandexactderivationofthetheor-eticalCrame´rRaolowerbound(CRLB)fortrackingmultipletargetsusingintensitymapsasmeasurements.Althoughtheformulationandthetheo

2、reticalderivationspresentedintheirworkareindeedcorrect,theanalysisoftheproposedboundandtheconclusionsthatfollowarewrong.Here,acorrectanalysisispresentedwiththekeyobservationthat[asopposedtotheclaimmadeintheworkofRisticetal.(2004)],theproposedCRLBreflectstheinteractionbetweenthetargets,e

3、veniftheirmotionisindependent.Themulti-targetCRLBisalsocomparedwiththeerrorperformanceofamulti-targetstatemaximumlikelihoodestimator;aremarkableagreementisobservedforhighsignal-to-noiseratio.1Introductionmainideainthisapproachistouserawdatabeforedetec-tionthresholdingasmeasurements,asi

4、tisdoneintheTracking(dataprocessing)involvestheestimationoftargettrack-before-detectparadigm[5].Thresholdingingeneralstates(positions,velocities,attributes)usingtheoutputisperformedtoreducethecomputationalloadofthefromasignalprocessingunitofasurveillancesystem,tracker,andinevitablycaus

5、essomelossofinformation.suchastheradar.Forafewdecades,therehavebeenThenthemultipletargettrackingcanbeformulatedasaattemptstoderivethetheoreticallybestachievabletrackingnonlinearfilteringproblemandtheCRLBcomputedviaerrorperformance[asafunctionofsensoraccuracy,theTichavskysrecursiveformul

6、a[6].Theresultingsignal-to-noiseratio(SNR),sensorresolutionandsoon],CRLBforunthresholdeddatawasreferredtoastheultimateintheformoftheCrame´rRaolowerbound(CRLB).CRLBintheworkofRisticetal.[4],sinceitrepresentstheSuchaboundwouldbeextremelyimportantasitcouldtrulybestachievabletrackingerrorp

7、erformance.Itturnsoutbeusedformanypracticalpurposes:trackingalgorithmthatthisCRLBdependsonpracticalengineeringparametersassessment,performanceprediction,trackingsystemofsurveillancesystemssuchasthesensorresolution,design,sensorallocationandscheduling[1],tonameafew.SNRandpoint-spreadf

当前文档最多预览五页,下载文档查看全文

此文档下载收益归作者所有

当前文档最多预览五页,下载文档查看全文
温馨提示:
1. 部分包含数学公式或PPT动画的文件,查看预览时可能会显示错乱或异常,文件下载后无此问题,请放心下载。
2. 本文档由用户上传,版权归属用户,天天文库负责整理代发布。如果您对本文档版权有争议请及时联系客服。
3. 下载前请仔细阅读文档内容,确认文档内容符合您的需求后进行下载,若出现内容与标题不符可向本站投诉处理。
4. 下载文档时可能由于网络波动等原因无法下载或下载错误,付费完成后未能成功下载的用户请联系客服处理。