A 201.4 GOPS 496 mW Real-Time Multi-Object Recognition Proce(2)

4040pixelsizedtile,calledagrid-tile.Fortheimplementationofvisualperceptionstage,aspecialhardwareblockwithbio-inspiredneuralnetworksandfuzzylogiccircuitsisproposedtomimicoperationsofhumanvisualsystem.

Thedescriptorgenerationstageextractskey-pointsofobjectsoutoftheselectedROIgrid-tilesfromthevisualperceptionstage,andgeneratesdescriptorvectorsforthem.Tothisend,variousalgorithmicmethodssuchasKLT,Harris-cornerdetector,af netransformations,andscaleinvariantfeaturetransform(SIFT)exist[6].Inouralgorithm,theSIFTisse-lectedbecauseitisrobusttonoiseinjectionaswellasscaleandrotationvariances.Fortheimplementationofdescriptorgenerationstage,aparallelprocessorconsistingofmanypro-cessingunitsisadoptedtotackleparallelandcompleximageprocessingtasks.Tobeapplicableforvariousalgorithms,eachprocessingunitisdesignedasaprogrammabledevice.

Theobjectdecisionstagedeterminesthe nalrecognitionre-sultsbyperformingdatabasematchingforselectedregions.Itmatchesthedescriptorvectorsoutofthedescriptorgenerationstagewiththeobjectdatabaseincludingthousandsofobjectvectors.Avectormatchingistosearchtheminimumdistancevectoroutofthevectorsinthedatabasewithaninputinquiryvector.Toacceleratetheserepeatedvectormatchingoperations,

A 201.4 GOPS real-time multi-object recognitionprocessor is presented with a three-stage pipelined architecture.Visual perception based multi-object recognition algorithm isapplied to give multiple attentions to multiple objects in the inputimage. For human-like multi-object perception, a neural perceptionengine is proposed with biologically inspired neural networksand fuzzy logic circ

34IEEEJOURNALOFSOLID-STATECIRCUITS,VOL.45,NO.1,JANUARY

2010

Fig.2.Three-stagemulti-objectrecognitionalgorithm.

dedicatedvectordistancecalculationunitsareemployedintheobjectdecisionstage.

Overall,theproposedalgorithmemploysgrid-basedROIpro-cessingthatdividestheinputimageintoanumberoftwo-di-mensional(2-D)grid-tilesandperformstheprocessingbasedonthem.Itenables ne-grainedROIextractionofmultipleob-jectsandreducestheeffectiveprocessingareaofinputimages.Toevaluatetheproposedalgorithm,weperformexperimentswith50of ceobjectsoutofColumbiaobjectimagelibrary(Coil-100)[10].Itisappliedto2400sampleimagesthatincluderandomobjectsinnaturalbackgroundscenes,witha16384-entrydatabasemadebytheSIFT.Asaresult,overallrecog-nitionratebytheproposedalgorithmismeasuredas92%.ForevaluationsoftheROIdetectionbyvisualperception,truepos-itiveratethatrepresentstheratioofcorrectlydetectedregionoutofgroundtruthROIandfalsepositiveratethatrepresentstheratioofincorrectlydetectedregionoutofnotinterestedre-gion[11]aremeasuredas70%and5%,respectively.Thevisualperceptionbarelyaffectstheoverallrecognitionratewhilere-ducingtheprocessingareaoftheimagesto32.8%onaverage.

III.SYSTEMARCHITECTURE

Fig.3showstheoverallblockdiagramoftheproposedpro-cessor.Itconsistsof21IPblocks:aneuralperceptionengine(NPE),aSPUtask/powermanager(STM),16SIMDprocessorunits(SPUs),adecisionprocessor(DP),andtwoexternalmemoryinterfaces.TheNPEisresponsibleforthe rstvisualperceptionstage.ItextractstheROIgrid-tilesforeachobjectandsendsthemto16SPUsfordetailedimageprocessing.The16SPUs,whosepowerdomainisseparatedintofour,areresponsiblefortheseconddescriptorgenerationstage.TheyextractobjectfeaturesoutoftheselectedROIsandconvertthemtodescriptorvectors.Thedescriptorvectorsoutofthe16SPUsaregatheredattheDP.TheDPacceleratesthevectormatchingprocessofdescriptorvectorsforthethirdobjectdecisionstage.TheSTMisspeciallydevisedtodistributethetasksoftheROIgrid-tilesfromtheNPEtothe16SPUsandtomanagethem.Italsocontrolsthepipelinestagesoftheoverallprocessorandmanagesfourpowerdomainsof16SPUs.Theoverall21IPblocksareinterconnectedthroughtheproposedmulti-castingNoC.

Toincreaseparallelismandhardwareutilizationofthepro-posedprocessor,theproposedthreestagesareexecutedinthepipelineinframelevelasshowninFig.4.ThepipelineddataareROIgrid-tilesanddescriptorvectorsbetweenthe rst–secondstageandsecond–thirdstage,respectively.Unliketheexecu-tiontimeofthe rstvisualperceptionstageisconstantduetoits xedcomputationamount,theexecutiontimeofthesecondde-scriptorgenerationandthirdobjectdecisionarevaryingwiththenumberofROIgrid-tilesanddescriptorvectors.Inordertobal-ancetheexecutiontimesofthreestages,theSTMestimatestheworkloadofthefollowingdescriptorvectorandobjectdecisionstagebasedonthenumberofextractedROIgrid-tilesandde-scriptorvectors,respectively,andcontrolstheirexecutiontimesusingtwopipelinetimebalancingschemes.

Tocontroltheexecutiontimeofthedescriptorgenerationstage,theSTMperformsworkload-awaretaskscheduling(WATS)thatdiffersthenumberofschedulingSPUsaccordingtothestage’sinputworkload.Fig.5(a)showsthe owchartoftheWATS.First,theSTMmeasuresthenumberofROIgrid-tilesfromtheNPEandclassi esittooneofNwork-loadlevelsdividedbyN-1thresholdvalues.Andthen,theSTMdeterminesthenumberofoperatingSPUsaccordingtotheclassi edworkloadlevel.SinceitallocatestheSPUsin

A 201.4 GOPS real-time multi-object recognitionprocessor is presented with a three-stage pipelined architecture.Visual perception based multi-object recognition algorithm isapplied to give multiple attentions to multiple objects in the inputimage. For human-like multi-object perception, a neural perceptionengine is proposed with biologically inspired neural networksand fuzzy logic circ

KIMetal.:A201.4GOPS496mWREAL-TIMEMULTI-OBJECTRECOGNITIONPROCESSORWITHBIO-INSPIREDNEURALPERCEPTIONENGINE

35

Fig.3.Overallblockdiagramofproposed

processor.

Fig.4.Three-stagepipelinedarchitecture.

proportionaltotheamountofworkload,theexecutiontimeoftheoveralldescriptorgenerationstageiskeptinconstant.Theoverallexecutiontimeisadjustedbymodifyingthresholdvaluesofclassi cationprocess.Byloweringthresholdvalues,theexecutiontimeisdecreasedbecausemoreSPUsareas-signedforthesameamountofworkload.Ontheotherhand,theexecutiontimeincreaseswhenthresholdvaluesbecomehigh,whilethenumberofoperatingSPUsisreduced.

Tocont …… 此处隐藏：6317字，全部文档内容请下载后查看。喜欢就下载吧 ……