遥感影像分类英文文献
ZHONGetal.:OBJECT-ORIENTEDCRFCLASSIFICATIONFRAMEWORKFORHSRREMOTESENSINGIMAGERY

7027
Fig.2.Relationshipbetweenlikelihoodandenergyvalue.(a)Logunarypotential.(b)Quasi-gammaunarypotential.
energy,whichhasbeenwidelyusedforremotesensingimageclassi cation,canbewrittenasthesumoftheunaryandpairwisepotentials,i.e.,
ψi(xi)+λψij(xi,xj)(6)E(x)=
i∈V
i∈V,j∈Ni
whereψi(xi)istheunarypotentialterm,andψijisthepairwise
potentialterm,whichiscomputedoverthelocalneighborhoodNiofpixeli.Thenonnegativeconstantλtradesoffthestrengthofthepairwisepotentialagainsttheunarypotential.
Aftertheestablishmentofthebasicmodel(6),aremainingproblemishowtoformulatethetwokindsofpotentials(i.e.,unaryandpairwisepotentials)andobtainthe nallabelsbyinference.
1)UnaryPotentials:Unarypotentialsdescribethecostofasinglepixeltakingaparticularlabel,whichdependsonthelocalappearancefeaturesderivedfromtheimage.Typically,theunarypotentialψi(xi)isde nedas[3],[32]
ψi(xi)= ln(P(xi=lk))
(7)
whereP(xi=lk)istheprobabilityofpixelxitakingthelabellk,whichcanbegivenbyvariousdiscriminativeclassi- ers.Inourwork,theseprobabilityestimatesarefrom“one-versus-one”SVMoutputs,asdescribedpreviously.Inordertoconvenientlydescribethedetailsofthealgorithm,wecalltheunarypotentialthe“logunarypotential”becauseofitslogfunctionform.
Theunarypotential’stermisrelatedtothepixelwisein-formation,andtheminimizationofonlythisterm’senergycontributionbyitselfwouldbeequivalenttoanoncontextualBayesianclassi cationoftheimage.Therefore,itshouldbelowwhenthecorrespondingpixeliscorrectlyclassi edandhighwhenitismisclassi ed.Thelogunarypotentialisfor-mulatedasthenegativeloglikelihoodofthepixeltakingtherelatedclasslabels.However,ifasmallobjectcontainingafewpixelswithhighlikelihoodispresentintheimage,thesepixelstendtobeassignedtheclasslabelofthesurroundingobjectsbecausethelogunarypotentialdoesnothaveenoughabilitytopreventthesmoothingofthepairwisepotentials.Inordertosuppresstheoversmoothingoftheclassi cationresult,thequasi-gammaunarypotentialisde ned
ψi(xi)=γ1/P(xi=lk) γ.
(8)
Fig.2(a)and(b)showstherelationshipbetweenthelikeli-hoodandtheenergyvalueofthelogandquasi-gammaunarypotentialswhenγ=2,respectively.Aswiththelogunarypotential,thequasi-gammaunarypotentialisalsomodeledasadecreasingfunctionoflikelihood.However,comparedwiththelogunarypotential,whentheprobabilitydensityestimateofthepixeltakingthecorrespondingclasslabelishigh,thepe-nalizationofthequasi-gammaunarypotentialisstilllow.Thismeansthatthelandcoverclasslabelofthepixelismaintainedinminimizingtheenergyfunctionwhenthecon denceofthepixeltakingtheclasslabelishigh.Inaddition,thepenalizationismuchgreaterwhenthelikelihoodisverylow,andevenwhenthelikelihoodis0.1,thispenalizationcanreach1024,whichimpliesthatthelandcoverclasslabelofthepixelisnotexpectedtobekeptwhenthecon denceisless.
2)PairwisePotentials:Pairwisepotentialsmodelasmooth-nesspriorthatencodesthefactthat,inrealimages,neighboringpixelsinhomogeneousimageregionsusuallytakethesamelabel.AsistypicalforpixellabelingwithCRF,thecontrast-sensitivesmoothnesspriorψij(xi,xj)takestheformof[32],[47],[48]
0,ifxi=xj
(9)ψij(xi,xj)=g(i,j)
,otherwisewhere
g(i,j)=1+θvexp θw xi xj 2.
Inthispaper,theedgefeaturefunctiong(i,j)isdesignedtomeasurethedifferenceinappearancebetweentheneighboringpixels.Theconstantincludeding(i,j)isabiastermtobelearnedforremovingsmallisolatedregions;thepairof(i,j)representsthespatiallocationofneighboringpixels;parameterθvisaconstantdeterminingthedegreeofsmoothness,andthequantityθwisthemeansquaredifferencebetweenthespectralvectorsoveralltheadjacentpixelsintheimage.
Thepairwisepotentialsincorporatethespatialcontextualinformationofeachpixel,whichisexpressedintermsofitsneighborhood,tobetakenintoaccountintheclassi cation.WhenminimizingtheenergyfunctionE(x),thecontrast-sensitivesmoothnesspriortermpenalizesthespatialinconsis-tenciesamongneighboringpixelswithdifferentclasslabels,whilefavoring,intheoutputclassi cationmap,thesameland
object as multiple instances and allowed the object to have multiple labels ... A Hybrid Conditional R... 11页 免费 Conditional Random Fie... 10页 ...
CVPR, 2007 Adaptive Contour Features in Oriented Granular Space for Human ... A Dynamic Conditional Random Field Model for Joint Labeling of Object and ...
A distributed object-oriented model for_专业资料。A distributed object-oriented model forA distributed object-oriented model for telecommunication services P....
A Haptic Object-Oriented Texture Rendering System Jason P. Fritz University of Delaware/A.I. duPont Institute Applied Science and Engineering Laboratories, ...
Object-Oriented Analysis 240页 免费 Designing test suites fo... 185页 ...We also introduce Frame-based Hidden-state Conditional Random Field model, a...
Even typical fact-oriented applications, such as information extraction, can ...er that combines a Conditional Random Field sequence tagging model (Lafferty ...
Even typical fact-oriented applications, such as information extraction, can ...er that combines a Conditional Random Field sequence tagging model (Lafferty ...
热门文档