英文资料快速的基于相位的多式联运图像数据配准Word文件下载.docx
《英文资料快速的基于相位的多式联运图像数据配准Word文件下载.docx》由会员分享,可在线阅读,更多相关《英文资料快速的基于相位的多式联运图像数据配准Word文件下载.docx(24页珍藏版)》请在冰豆网上搜索。
Received19July2008;
revised14October2008;
accepted18October2008.
Availableonline5November2008.
Abstract
Aninterestingprobleminpatternrecognitionisthatofimageregistration,whichplaysanimportantroleinmanyvision-basedrecognitionandmotionanalysisapplications.Ofparticularinterestamongregistrationproblemsaremultimodalregistrationproblems,wheretheimagesexistindifferentfeaturespaces.State-of-the-artphased-basedapproachestomultimodalimageregistrationmethodshaveprovidedgoodaccuracybuthavehighcomputationalcost.Thispaperpresentsafastphase-basedapproachtoregisteringmultimodalimagesforthepurposeofinitialcoarse-grainedregistration.Thisisaccomplishedbysimultaneouslyperformingbothgloballyexhaustivedynamicphasesub-cloudmatchingandpolynomialfeaturespacetransformationestimationinthefrequencydomainusingthefastFouriertransform(FFT).Amultiscalephase-basedfeatureextractionmethodisproposedthatdeterminesboththelocationandsizeofthedynamicsub-cloudsbeingextracted.Asimpleoutlierpruningbasedonresamplingisusedtoremovefalsekeypointmatches.Theproposedphase-basedapproachtoregistrationcanbeperformedveryefficientlywithouttheneedforinitialestimatesorequivalentkeypointsfrombothimages.Experimentalresultsshowthattheproposedmethodcanprovideaccuraciescomparabletothestate-of-the-artphase-basedimageregistrationmethodsforthepurposeofinitialcoarse-grainedregistrationwhilebeingmuchfastertocompute.
Keywords:
Imageregistration;
Phase;
FastFouriertransform;
Multimodal;
Keypoints;
Dynamicsub-clouds
ArticleOutline
1.Introduction
2.Multimodalregistrationproblem
3.Previouswork
4.Proposedregistrationalgorithm
4.1.Keypointdetectionandsub-cloudsizeestimation
4.2.Phasesub-cloudextraction
4.3.Simultaneoussub-cloudmatchingandfeaturespacetransformationestimation
4.4.Solvingthesimultaneousmatchingandfeaturespacetransformationestimationprobleminthefrequencydomain
4.5.Outlierpruningthroughresampling
4.6.Algorithmoutline
5.Computationalcomplexityanalysis
6.Experimentalresults
7.Conclusionsandfuturework
Acknowledgements
References
1.Introduction
Imageregistrationistheprocessofmatchingpointsinoneimagetotheircorrespondingpointsinanotherimage.Theproblemofimageregistrationplaysaveryimportantroleinmanyvisualandobjectrecognitionandmotionanalysisapplications.Someoftheseapplicationsincludevisualmotionestimation[1]and[2],vision-basedcontent-basedretrieval[3]and[4],imageregistration[5],[6],[7]and[9],andbiometricauthentication[10].Inthebestcasescenario,theimagesexistatthesamescale,inthesameorientation,aswellasrepresentedinthesamefeaturespace.However,thisisnotthecaseinmostreal-worldapplications.Therearemanysituationswheretheimagesexistindifferentfeaturespaces.Thisparticularproblemwillbereferredtoasthemultimodalregistrationproblemandisaparticularlydifficultproblemtosolve.Examplesofthisprobleminreal-worldsituationsincludemedicalimageregistrationandtrackingofMRI/CT/PETdata[11]andbuildingmodelingandvisualizationusingLIDARandopticaldata[12]and[13].
Thereareseveralimportantissuesthatmakemultimodalregistrationadifficultproblemtosolve.First,manyregistrationalgorithmsrequirethatequivalentkeypointsbeidentifiedwithineachimage.However,giventhedifferencesbetweenfeaturespacesinwhichtheimagesexist,itisoftenaverydifficulttask.Thesignificantdifferencesbetweenfeaturespacesalsomakeitimpracticaltoperformdirectintensitymatchingbetweenthetwoimages.Inrecentyears,aneffectiveapproachtomultimodalregistrationhasbeenproposedthatutilizeslocalphase[14]and[15].Thisstate-of-the-artapproachevaluatesthemutualinformationbetweenthelocalphaseoftwoimagestodeterminetheoptimalalignmentandhasbeenshowntobeveryeffectiveatmatchingmultimodalmedicalimagedata,outperformingexistingmultimodalregistrationmethods[14]and[15].However,thisapproachiscomputationallyexpensive(O(N6)forthemutualinformationevaluationprocess).Assuch,aregistrationmethodthatisabletotakeadvantageoflocalphaseinformationtodeterminepointcorrespondencesbetweenimageswhilebeingcomputationallyefficientishighlydesiredforthepurposeofinitialcoarse-grainedregistration.
Themaincontributionofthispaperisfastphase-basedregistrationalgorithmforaligningmultimodalimages.Theproposedmethodisdesignedtoprovideafastalternativeto