




版權說明:本文檔由用戶提供并上傳,收益歸屬內(nèi)容提供方,若內(nèi)容存在侵權,請進行舉報或認領
文檔簡介
OverviewOverviewPart1:ReviewofObjectTracking?SingleObjectTracking(SOT)?VideoObjectSegmentation(VOS)?MultipleObjectTracking(MOT)?Multi-ObjectTrackingandSegmentation(MOTS)?SummaryPart2:TowardsGrandUnificationofObjectTracking?GeneralVisionModels(GVM)?UnificationofObjectTracking?Unicorn?Experiments?FurtherAnalysis PartPart1:ReviewofObjectTracking?SingleObjectTracking(SOT)?VideoObjectSegmentation(VOS)?MultipleObjectTracking(MOT)?Multi-ObjectTrackingandSegmentation(MOTS) SingleSingleObjectTracking(SOT)TrackanarbitraryobjectinavideogivenitsinitiallocationSingle-object,Any-classOcclusion,LightChange,BackgroundClutter,etc. zCorrHead !Online !Head !TransformerzHeadxfffSingleObjectTrackingzCorrHead !Online !Head !TransformerzHeadxfffSingleObjectTracking(SOT)SiameseRPNf !fx?SiamRPN(CVPR18)?DaSiamRPN(ECCV18)?SiameRPN++(CVPR19)?Ocean(ECCV20)zDCFx?ATOM(CVPR19)?DiMP(ICCV19)?PrDiMP(CVPR20)?KYS(ECCV20)f !fTransf !f?TransT(CVPR21)?STARK(ICCV21)MostSOTmethodsarebasedonthesearchregion.Pros:Cons:?SavingcomputationV.S?Sensitivetotemporarytrackingfailure?Filteringoutdistractors?Time-consumingwhennumofobjectsislarge UnsupervisedVOSReferringUnsupervisedVOSReferringVOSVideoObjectSegmentation(VOS)nGoalnSegmentspecificobjectspreciselyinavideo.SegmentsalientmovingobjectSemi-supervisedVOSSegmentobjectsgiveninthe1stframebymasksSegmentobjectsgiveninthe1stframebylanguageSTM(ICCVSTM(ICCV19)CFBI(ECCV20)STCN(NeurIPS21)VideoObjectSegmentation(VOS)Semi-supervisedVOSisdominatedbySpace-TimeMemoryNetworkAlthoughachievinggreatperformance,STM-basedmethodssufferfromthefollowingdisadvantages:?Hugetimeandspacecomplexity,especiallyforhighspatialresolutionandthelongsequence.?Highlyrelyingonhigh-qualitymaskannotationsonthefirstframe.MultipleObjectMultipleObjectTracking(MOT)nGoalnTrackallobjectsofspecificclassesinavideo.MOTChallengeBDD100KVisdrone(1class:Person)(8classes:Car,pedestrian,etc)(10classes:Car,pedestrian,etc)ParadigmParadigmMultipleObjectTracking(MOT)RepresentativeMethodsuTrackingbyDetectionuTrackingbyDetection(SORT,DeepSORT,StrongSORT)uJointDetectionandTrackinguJointDetectionandTracking(JDE,FairMOT,CenterTrack,QDTrack)(TrackFormer,GTR)MOTmethodstakesthehigh-resolutionwholeimageastheinputtodetectobjectsascompletelyaspossible.Multi-ObjectTrackingandSegmentation(MOTS)nGoalnSegmentallobjectsofspecificclassesinavideo.MOTSChallengeBDD100KMOTS(1class:Person)(8classes:Car,pedestrian,etc)MOTScanbeseenasavariantofMOTbyreplacingboxeswithmasks.SummarSummaryReferenceOutputsClassTrackspervideoRepresentativeMethodsTypicalInputsSOTInitialboxBoxesagnosticOneOne-ShotDetectionSmallsearchregionVOSInitialmaskMasksagnosticSeveralSTMMedium-resolutionWholeImageMOTNOBoxesspecificTensorhundredsDetection+AssociationHigh-resolutionWholeImageMOTSNOMasksspecificTensorhundredsDetection+AssociationHigh-resolutionWholeImagettherearelargegapsbetweenthefourtrackingtasks?GeneralVisionModels(GVM)?UnificationofObjectTracking?Unicorn?Experiments?FurtherAnalysis entAIvsAGI–CurrentweakAIisdesignedforsolvingonespecifictask.–Artificialgeneralintelligence(AGI)isexpectedtounderstandorlearnanyintellectualtaskthatahumanbeingcan. ?Pioneeringworksinthepastyear2021.082021.112021.112022.01ies Threeobstacleshinderingtheunification:(1)Thecharacteristicsoftrackedobjectsvary(onetargetofanyclassgiveninthereferenceframev.stensevenhundredsofinstancesofspecificcategories)(2)SOTandMOTrequiredifferenttypesofcorrespondence.(pixel-levelcorrespondencedistinguishingthetargetfromthebackgroundv.sinstance-levelcorrespondencematchingthecurrentlydetectedobjectswithprevioustrajectories)(3)DifferentInputs.(smallsearchregiontosavecomputationandfilterpotentialdistractorsv.shigh-resolutionfullimagefordetectinginstancesascompleteaspossible) ?WeproposeUnicorn,aunifiedsolutionforSOT,MOT,VOSandMOTS.?Unicornaccomplishesthegreatunificationofthenetworkarchitectureandthelearningparadigmforfourtrackingtasks.?Unicornputsforwardsnewstate-of-the-artperformanceonmultiplechallengingtrackingbenchmarkswiththesamemodelparameters. Unifiedinputsandbackbone?Takingthefullimagesasinputsforalltasks.?Referenceframeisthe1stframeforSOT&VOSandthe(t-1)thframeforMOT&MOTS?Oneunifiedbackbone(ConvNeXtbydefault)ErefeRhwxcEcureRhwxcCpixeRhwxhwForMOT&MOTS,TheinstanceembeddingeisextractedfromtheframeembeddingE,wherethecenteroftheinstanceislocatederefeRMxc,ecureRNxcCinsteRNxMCinstisthesub-matrixofCpixLearninghighlydiscriminativeembedding{Eref,Ecur}isthekeytobuildingprecisecorrespondenceforalltrackingtasks.Aninteractionmoduleisusedtoenhancedtheoriginalimagefeature.Bydefaultweusethedeformableattentionblockforinteraction.LearningCorrespondencebyPropagation&LearningCorrespondencebyPropagation&Association.?ForSOT&VOS,Correspondencehelpstopropagatethetargetmapfromthereferenceframetothecurrentframe.?ForMOT&MOTS,Correspondencehelpstomatchthedetectionsonthecurrentframewiththetrajectoriesonthereferenceframe.Weintroducethetargetpriorastheswitchamongfourtrackingtasks.?ForSOT&VOS,thetargetpriorcanenhancetheoriginalFPNfeatureandmakesthenetworkfocusonthetrackedtarget.?ForMOT&MOTS,thefusedfeatureF′degeneratesbacktotheoriginalFPNfeatureFtodetectobjectsofspecificclasses.ObjectObjectdetectionheadbasedonYOLOXandCondInst?One-stage,anchor-free?NoRoIoperationssuchasRoI-AlignYOLOXHeadforobjectdetectionCondInstHeadforinstancesegmentationAddthemaskbranchandfreezeotherparametersStage1Target:Correspondence+DetectionLoss:Lstage1=Lcorr+LdetData:1:1fromSOT&MOTSOT:weuseCOCO,LaSOT,GOT-10KandTrackingNetMOT:?ForMOT17,weuseCrowdhuman,ETHZ,CityPerson,MOT17?ForBDD100K,weuseBDD100KStage2Target:MaskLoss:Lstage2=LmaskData:1:1fromVOS&MOTSVOS:weuseCOCO,DAVIS,Youtube-VOSMOTS:?ForMOTS,weuseCOCOandMOTS?ForBDD100K,weuseBDD100K?TrainingofVOS&MOTSwouldnotimpacttheperformanceofSOT&MOT.ForuserswhoareonlyinterestedintheSOT&MOT,runningStage1isenough.?Ineachstage,wetrainthemodel
溫馨提示
- 1. 本站所有資源如無特殊說明,都需要本地電腦安裝OFFICE2007和PDF閱讀器。圖紙軟件為CAD,CAXA,PROE,UG,SolidWorks等.壓縮文件請下載最新的WinRAR軟件解壓。
- 2. 本站的文檔不包含任何第三方提供的附件圖紙等,如果需要附件,請聯(lián)系上傳者。文件的所有權益歸上傳用戶所有。
- 3. 本站RAR壓縮包中若帶圖紙,網(wǎng)頁內(nèi)容里面會有圖紙預覽,若沒有圖紙預覽就沒有圖紙。
- 4. 未經(jīng)權益所有人同意不得將文件中的內(nèi)容挪作商業(yè)或盈利用途。
- 5. 人人文庫網(wǎng)僅提供信息存儲空間,僅對用戶上傳內(nèi)容的表現(xiàn)方式做保護處理,對用戶上傳分享的文檔內(nèi)容本身不做任何修改或編輯,并不能對任何下載內(nèi)容負責。
- 6. 下載文件中如有侵權或不適當內(nèi)容,請與我們聯(lián)系,我們立即糾正。
- 7. 本站不保證下載資源的準確性、安全性和完整性, 同時也不承擔用戶因使用這些下載資源對自己和他人造成任何形式的傷害或損失。
最新文檔
- 建筑工程安全隱患排查方案
- 混凝土施工中砂石質(zhì)量監(jiān)控方案
- 水稻脫險計課件
- 混凝土施工中的表面防水層施工方案
- 陶瓷造型工藝35課件
- 人防工程建設驗收標準與流程
- 2025中國視神經(jīng)脊髓炎譜系疾病診斷與治療指南解讀課件
- 乙型肝炎病毒山東醫(yī)學高等專科學校劉琳琳47課件
- 信息技術(Kylin系統(tǒng)+WPS辦公+AI賦能)教案 項目4 錄入與編排技術服務合同
- 二零二五年度環(huán)保產(chǎn)業(yè)園區(qū)建設項目承包工程合同范本
- GB/T 33365-2016鋼筋混凝土用鋼筋焊接網(wǎng)試驗方法
- GB/T 12750-2006半導體器件集成電路第11部分:半導體集成電路分規(guī)范(不包括混合電路)
- 《乒乓裁判規(guī)則規(guī)程》考試題庫(附答案)
- 依托自主化裝備建設分布式能源三聯(lián)供項目
- 老年肌肉衰減綜合征(肌少癥)課件
- 山西省持有《危險廢物經(jīng)營許可證》單位一覽表
- PCB全制程培訓教材
- 煙草配送車輛GPS管理方案
- 中圖法分類號與中圖分類法查詢
- 開音節(jié)閉音節(jié)中元音字母的發(fā)音規(guī)律練習
- 電力設備預防性試驗及維護保養(yǎng)方案
評論
0/150
提交評論