14 Pages
English

What Where How Many Combining Object Detectors and CRFs

-

Gain access to the library to view online
Learn more

Description

Niveau: Supérieur, Doctorat, Bac+8
What, Where & How Many? Combining Object Detectors and CRFs L'ubor Ladick?, Paul Sturgess, Karteek Alahari, Chris Russell, and Philip H.S. Torr ? Oxford Brookes University Abstract. Computer vision algorithms for individual tasks such as object recog- nition, detection and segmentation have shown impressive results in the recent past. The next challenge is to integrate all these algorithms and address the prob- lem of scene understanding. This paper is a step towards this goal. We present a probabilistic framework for reasoning about regions, objects, and their attributes such as object class, location, and spatial extent. Our model is a Conditional Ran- dom Field defined on pixels, segments and objects. We define a global energy function for the model, which combines results from sliding window detectors, and low-level pixel-based unary and pairwise relations. One of our primary con- tributions is to show that this energy function can be solved efficiently. Exper- imental results show that our model achieves significant improvement over the baseline methods on CamVid and PASCAL VOC datasets. 1 Introduction Scene understanding has been one of the central goals in computer vision for many decades [1]. It involves various individual tasks, such as object recognition, image seg- mentation, object detection, and 3D scene recovery. Substantial progress has been made in each of these tasks in the past few years [2–6].

  • improvement over

  • segmentation

  • problems such

  • crf

  • potential function

  • crf can

  • based move

  • vision challenges

  • early vision tasks


Subjects

Informations

Published by
Reads 14
Language English
What,Where&HowMany?CombiningObjectDetectorsandCRFsL'uborLadický,PaulSturgess,KarteekAlahari,ChrisRussell,andPhilipH.S.TorrOxfordBrookesUniversityhttp://cms.brookes.ac.uk/research/visiongroupAbstract.Computervisionalgorithmsforindividualtaskssuchasobjectrecog-nition,detectionandsegmentationhaveshownimpressiveresultsintherecentpast.Thenextchallengeistointegrateallthesealgorithmsandaddresstheprob-lemofsceneunderstanding.Thispaperisasteptowardsthisgoal.Wepresentaprobabilisticframeworkforreasoningaboutregions,objects,andtheirattributessuchasobjectclass,location,andspatialextent.OurmodelisaConditionalRan-domFielddenedonpixels,segmentsandobjects.Wedenealgobalenergyfunctionforthemodel,whichcombinesresultsfromslidingwindowdetectors,andlow-levelpixel-basedunaryandpairwiserelations.Oneofourprimarycon-tributionsistoshowthatthisenergyfunctioncanbesolvedefciently.Exper-imentalresultsshowthatourmodelachievessignicantimprovementoverthebaselinemethodsonCamVidandPASCALVOCdatasets.1IntroductionSceneunderstandinghasbeenoneofthecentralgoalsincomputervisionformanydecades[1].Itinvolvesvariousindividualtasks,suchasobjectrecognition,imageseg-mentation,objectdetection,and3Dscenerecovery.Substantialprogresshasbeenmadeineachofthesetasksinthepastfewyears[2–6].Inlightofthesesuccesses,thechal-lengingproblemnowistoputtheseindividualelementstogethertoachievethegrandgoal—sceneunderstanding,aproblemwhichhasreceivedincreasingattentionre-cently[6,7].Theproblemofsceneunderstandinginvolvesexplainingthewholeim-agebyrecognizingalltheobjectsofinterestwithinanimageandtheirspatialextentorshape.Thispaperisasteptowardsthisgoal.Weaddresstheproblemsofwhat,where,andhowmany:werecognizeobjects,ndtheirlocationandspatialextent,seg-mentthem,andalsoprovidethenumberofinstancesofobjects.Thisworkcanbeviewedasanintegrationofobjectclasssegmentationmethods[3],whichfailtodis-tinguishbetweenadjacentinstancesofobjectsofthesameclass,andobjectdetectionapproaches[4],whichdonotprovideinformationaboutbackgroundclasses,suchasgrass,skyandroad.Theproblemofsceneunderstandingisparticularlychallenginginscenescomposedofalargevarietyofclasses,suchasroadscenes[8]andimagesinthePASCALVOCThisworkissupportedbyEPSRCresearchgrants,HMGCC,theISTProgrammeoftheEu-ropeanCommunity,underthePASCAL2NetworkofExcellence,IST-2007-216886.P.H.S.TorrisinreceiptofRoyalSocietyWolfsonResearchMeritAward.