基于视觉的矿井救援机器人场景识别英文文献翻译可编辑.docx

基于视觉的矿井救援机器人场景识别英文文献翻译可编辑.docx

《基于视觉的矿井救援机器人场景识别英文文献翻译可编辑.docx》由会员分享，可在线阅读，更多相关《基于视觉的矿井救援机器人场景识别英文文献翻译可编辑.docx（10页珍藏版）》请在冰豆网上搜索。

基于视觉的矿井救援机器人场景识别英文文献翻译可编辑

基于视觉的矿井救援机器人场景识别--英文文献翻译

附录A英文原文

Scenerecognitionforminerescuerobot

localizationbasedonvision

CUIYi-an崔益安,CAIZi-xing蔡自兴,WANGLu王璐

Abstract:

AnewscenerecognitionsystemwaspresentedbasedonfuzzylogicandhiddenMarkovmodelHMMthatcanbeappliedinminerescuerobotlocalizationduringemergencies.Thesystemusesmonocularcameratoacquireomni-directionalimagesofthemineenvironmentwheretherobotlocates.Byadoptingcenter-surrounddifferencemethod,thesalientlocalimageregionsareextractedfromtheimagesasnaturallandmarks.TheselandmarksareorganizedbyusingHMMtorepresentthescenewheretherobotis,andfuzzylogicstrategyisusedtomatchthesceneandlandmark.Bythisway,thelocalizationproblem,whichisthescenerecognitionprobleminthesystem,canbeconvertedintotheevaluationproblemofHMM.Thecontributionsoftheseskillsmakethesystemhavetheabilitytodealwithchangesinscale,2Drotationandviewpoint.Theresultsofexperimentsalsoprovethatthesystemhashigherratioofrecognitionandlocalizationinbothstaticanddynamicmineenvironments.

Keywords:

robotlocation;scenerecognition;salientimage;matchingstrategy;fuzzylogic;hiddenMarkovmodel

1Introduction

Searchandrescueindisasterareainthedomainofrobotisaburgeoningandchallengingsubject[1].Minerescuerobotwasdevelopedtoenterminesduringemergenciestolocatepossibleescaperoutesforthosetrappedinsideanddeterminewhetheritissafeforhumantoenterornot.Localizationisafundamentalprobleminthisfield.Localizationmethodsbasedoncameracanbemainlyclassifiedintogeometric,topologicalorhybridones[2].Withitsfeasibilityandeffectiveness,scenerecognitionbecomesoneoftheimportanttechnologiesoftopologicallocalization.

Currentlymostscenerecognitionmethodsarebasedonglobalimagefeaturesandhavetwodistinctstages:

trainingofflineandmatchingonline.

Duringthetrainingstage,robotcollectstheimagesoftheenvironmentwhereitworksandprocessestheimagestoextractglobalfeaturesthatrepresentthescene.Someapproacheswereusedtoanalyzethedata-setofimagedirectlyandsomeprimaryfeatureswerefound,suchasthePCAmethod[3].However,thePCAmethodisnoteffectiveindistinguishingtheclassesoffeatures.Anothertypeofapproachusesappearancefeaturesincludingcolor,textureandedgedensitytorepresenttheimage.Forexample,ZHOUetal[4]usedmultidimensionalhistogramstodescribeglobalappearancefeatures.Thismethodissimplebutsensitivetoscaleandilluminationchanges.Infact,allkindsofglobalimagefeaturesaresufferedfromthechangeofenvironment.

LOWE[5]presentedaSIFTmethodthatusessimilarityinvariantdescriptorsformedbycharacteristicscaleandorientationatinterestpointstoobtainthefeatures.Thefeaturesareinvarianttoimagescaling,translation,rotationandpartiallyinvarianttoilluminationchanges.ButSIFTmaygenerate1000ormoreinterestpoints,whichmayslowdowntheprocessordramatically.

Duringthematchingstage,nearestneighborstrategyNNiswidelyadoptedforitsfacilityandintelligibility[6].Butitcannotcapturethecontributionofindividualfeatureforscenerecognition.Inexperiments,theNNisnotgoodenoughtoexpressthesimilaritybetweentwopatterns.Furthermore,theselectedfeaturescannotrepresentthescenethoroughlyaccordingtothestate-of-artpatternrecognition,whichmakesrecognitionnotreliable[7].

Sointhisworkanewrecognitionsystemispresented,whichismorereliableandeffectiveifitisusedinacomplexmineenvironment.Inthissystem,weimprovetheinvariancebyextractingsalientlocalimageregionsaslandmarkstoreplacethewholeimagetodealwithlargechangesinscale,2Drotationandviewpoint.Andthenumberofinterestpointsisreducedeffectively,whichmakestheprocessingeasier.FuzzyrecognitionstrategyisdesignedtorecognizethelandmarksinplaceofNN,whichcanstrengthenthecontributionofindividualfeatureforscenerecognition.Becauseofitspartialinformationresumingability,hiddenMarkovmodelisadoptedtoorganizethoselandmarks,whichcancapturethestructureorrelationshipamongthem.SoscenerecognitioncanbetransformedtotheevaluationproblemofHMM,whichmakesrecognitionrobust.

2Salientlocalimageregionsdetection

Researchesonbiologicalvisionsystemindicatethatorganismlikedrosophilaoftenpaysattentiontocertainspecialregionsinthescenefortheirbehavioralrelevanceorlocalimagecueswhileobservingsurroundings[8].Theseregionscanbetakenasnaturallandmarkstoeffectivelyrepresentanddistinguishdifferentenvironments.Inspiredbythose,weusecenter-surrounddifferencemethodtodetectsalientregionsinmulti-scaleimagespaces.Theopponenciesofcolorandtexturearecomputedtocreatethesaliencymap.

Follow-up,sub-imagecenteredatthesalientpositioninSistakenasthelandmarkregion.Thesizeofthelandmarkregioncanbedecidedadaptivelyaccordingtothechangesofgradientorientationofthelocalimage[11].

Mobilerobotnavigationrequiresthatnaturallandmarksshouldbedetectedstablywhenenvironmentschangetosomeextent.Tovalidatetherepeatabilityonlandmarkdetectionofourapproach,wehavedonesomeexperimentsonthecasesofscale,2Drotationandviewpointchangesetc.Fig.1showsthatthedoorisdetectedforitssaliencywhenviewpointchanges.Moredetailedanalysisandresultsaboutscaleandrotationcanbefoundinourpreviousworks[12].

3Scenerecognitionandlocalization

Differentfromotherscenerecognitionsystems,oursystemdoesn’tneedtrainingoffline.Inotherwords,ourscenesarenotclassifiedinadvance.Whenrobotwanders,scenescapturedatintervalsoffixedtimeareusedtobuildthevertexofatopologicalmap,whichrepresentstheplacewhererobotlocates.Althoughthemap’sgeometriclayoutisignoredbythelocalizationsystem,itisusefulforvisualizationanddebugging[13]andbeneficialtopathplanning.Solocalizationmeanssearchingthebestmatchofcurrentsceneonthemap.InthispaperhiddenMarkovmodelisusedtoorganizetheextractedlandmarksfromcurrentsceneandcreatethevertexoftopologicalmapforitspartialinformationresumingability.

Resembledbypanoramicvisionsystem,robotlooksaroundtogetomni-images.From

Fig.1Experimentonviewpointchanges

eachimage,salientlocalregionsaredetectedandformedtobeasequence,namedaslandmarksequencewhoseorderisthesameastheimagesequence.ThenahiddenMarkovmodeliscreatedbasedonthelandmarksequenceinvolvingksalientlocalimageregions,whichistakenasthedescriptionoftheplacewheretherobotlocates.InoursystemEVI-D70camerahasaviewfieldof±170°.Consideringtheoverlapeffect,wesampleenvironmentevery45°toget8imagesLetthe8imagesashiddenstateSi1≤i≤8,thecreatedHMMcanbeillustratedbyFig.2.TheparametersofHMM,aijandbjk,areachievedbylearning,usingBaulm-Welchalgorithm[14].Thethresholdofconvergenceissetas0.001.

Asfortheedgeoftopologicalmap,weassignitwithdistanceinformationbetweentwovertices.Thedistancescanbecomputedaccordingtoodometryreadings.

Fig.2HMMofenvironment

Tolocateitselfonthetopologicalmap,robotmustrunits‘eye’onenvironmentandextractalandmarksequenceL1′Lk′,thensearchthemapforthebestmatchedvertexscene.Differentfromtraditionalprobabilisticlocalization[15],inoursystemlocalizationproblemcanbeconvertedtotheevaluationproblemofHMM.Thevertexwiththegreatestevaluationvalue,whichmustalsobegreaterthanathreshold,istakenasthebestmatchedvertex,whichindicatesthemostpossibleplacewheretherobotis.

4Matchstrategybasedonfuzzylogic

Oneofthekeyissuesinimagematchproblemistochoosethemosteffectivefeaturesordescriptorstorepresenttheoriginalimage.Duetorobotmovement,thoseextractedlandmarkregionswillchangeatpixellevel.So,thedescriptorsorfeatureschosenshouldbeinvarianttosomeextentaccordingtothechangesofscale,rotationandviewpointetc.Inthispaper,weuse4featurescommonlyadoptedinthecommunitythatarebrieflydescribedasfollows.

GO:

Gradientorientation.Ithasbeenprovedthatilluminationandrotationchangesarelikelytohavelessinfluenceonit[5].

ASMandENT:

Angularsecondmomentandentropy,whicharetwotexturedescriptors.

H:

Hue,whichisusedtodescribethefundamentalinformationoftheimage.

Anotherkeyissueinmatchproblemistochooseagoodmatchstrategyoralgorithm.UsuallynearestneighborstrategyNNisusedtomeasurethesimilaritybetweentwopatterns.ButwehavefoundintheexperimentsthatNNcan’tadequatelyexhibittheindividualdescriptororfeature’scontributiontosimilaritymeasurement.AsindicatedinFig.4,theinputimageFig.4acomesfromdifferentviewofFig.4b.ButthedistancebetweenFigs.4aandbcomputedbyJeffereydivergenceislargerthanFig.4c.

Tosolvetheproblem,wedesignanewmatchalgorithmbasedonfuzzylogicforexhibitingthesubtlechangesofeachfeatures.Thealgorithmisdescribedasbelow.

Andthelandmarkinthedatabasewhosefusedsimilaritydegreeishigherthananyothersistakenasthebestmatch.ThematchresultsofFigs.2bandcaredemonstratedbyFig.3.Asindicated,thismethodcanmeasurethesimilarityeffectivelybetweentwopatterns.

Fig.3Similaritycomputedusingfuzzystrategy

5Experimentsandanalysis

Thelocalizationsystemhasbeenimplementedonamobilerobot,whichi