Robust description and recognition of various viewpoint dynamic textures

在线阅读 下载PDF 导出详情
摘要 Theproblemofrecognizingnaturalscenes,suchaswater,smoke,fire,wind-blownvegetationandaflockofflyingbirds,isconsidered.Thesescenesexhibitthecharacteristicdynamicpattern,buthavestochasticextent.Theyarereferredtoasdynamictexture(DT).Inreality,thediversityofDTsondifferentviewpointsandscalesareverycommon,whichalsobringgreatdifficultytorecognizeDTs.Inthepreviousstudies,duetonoconsideringofthedeformableandtransientnatureofelementsinDT,themotionestimationmethodisbasedonbrightnessconstancyassumption,whichseeminappropriateforaggregateandcomplexmotions.Anovelmotionmodelbasedonrelativemotionintheneighborhoodoftwo-dimensionalmotionfieldsisproposed.Theestimationofnon-rigidmotionofDTsisbasedonthecontinuityequation,andthenthelocalvectordifference(LVD)isproposedtocharacterizeDTlocalrelativemotion.SpatiotemporalstatisticsoftheLVDsisusedastherepresentationofDTsequences.ExcellentperformancesofclassifyingallDTsinUCLAdatabasedemonstratethecapabilityoftheproposedmethodindescribingDT.
机构地区 不详
出版日期 2016年04月14日(中国期刊网平台首次上网日期,不代表论文的发表时间)