Abstract. Color can provide an e#cient visual feature for tracking nonrigid objects in real-time. However, the color of an object can vary over time dependent on the illumination, the visual angle and the camera parameters. To handle these appearance chang
ObjectTrackingwithanAdaptive
Color-BasedParticleFilter
KatjaNummiaro1,EstherKoller-Meier2,andLucVanGool1,2
KatholiekeUniversiteitLeuven,ESAT/VISICS,Belgium
{knummiar,vangool}@esat.kuleuven.ac.be
SwissFederalInstituteofTechnology(ETH),D-ITET/BIWI,Switzerland
{ebmeier,vangool}@vision.ee.ethz.ch12
Abstract.Colorcanprovideane cientvisualfeaturefortrackingnon-rigidobjectsinreal-time.However,thecolorofanobjectcanvaryovertimedependentontheillumination,thevisualangleandthecameraparameters.Tohandletheseappearancechangesacolor-basedtargetmodelmustbeadaptedduringtemporallystableimageobservations.Thispaperpresentstheintegrationofcolordistributionsintoparticle lteringandshowshowthesedistributionscanbeadaptedovertime.Aparticle ltertracksseveralhypothesessimultaneouslyandweightsthemaccordingtotheirsimilaritytothetargetmodel.AssimilaritymeasurebetweentwocolordistributionsthepopularBhattacharyyacoe cientisapplied.Inordertoupdatethetargetmodeltoslowlyvaryingimageconditions,frameswheretheobjectisoccludedortoonoisymustbediscarded.
1Introduction
Objecttrackingisrequiredbymanyvisionapplications,butespeciallyinvideotechnology[2,5,7,12].Trackingmethodscanbedividedintotwomainclassesspeci edasbottom-uportop-downapproaches.Inabottom-upapproachtheimageisgenerallysegmentedintoobjectswhicharethenusedforthetracking.Forexampleblobdetection[12]canbeusedfortheobjectextraction.Incontrast,atop-downapproachgeneratesobjecthypothesesandtriestoverifythemusingtheimage.Typically,model-based[5,7]ortemplatematchingapproaches[2]comprisethisclass.Theproposedparticle lterwithcolor-basedimagefeaturesbelongstothetop-downapproachesastheimagecontentisonlyevaluatedatthehypotheticalobjectpositions.
Theideaofaparticle lter–toapplyarecursiveBayesian lterbasedonsamplesets–wasindependentlyproposedbyseveralresearchgroups[3,5,7,11].These ltersproviderobusttrackingframeworksastheyareneitherlimitedtolinearsystemsnorrequirethenoisetobeGaussian.Inthispaperwepresenttheintegrationofcolordistributionsintoparticle ltering,whichhastypicallyusededge-basedimagefeatures[4,5,7,13].Colorhistogramshavemanyadvantagesfortrackingnon-rigidobjectsastheyarerobusttopartialocclusion,arerotationandscaleinvariantandarecalculatede ciently.In[8]colorinformationhas
Van Gool, Object Tracking with an Adaptive Color-Based Particle Filter, Symposium for Pattern Recognition of the DAGM (2002) 353-360. [25] P. P?rez...
An Adaptive Color-Based ... 22页 免费 Object tracking with an ... 8... an Adaptive UKF-Based Particle Filter for Mobile Robot SLAM 基于自适应UKF...
Visual Object Tracking i... 5页 免费 An Adaptive Color-Based ... 22... Color-Based Road Sign De... 暂无评价 10页 免费 Particle filter with ...
Color Based Probabilistic Particle Filter Iteration Steps: Initialize xt for ... Object tracking with a... 8页 免费 Adaptive Object Tracki... 6页 免费...
An adaptive particle filter for mobile robot fault diagnosis_专业资料。维普资讯 http://www.cqvip.com JCn.ot nvTcn1f060—690 .etSuhUi.eho.20)608—5Do...
Object tracking with a... 8页 免费 Model-...an Adaptive Color Model Gi-jeong Jang and In-... apply the motion model to each particle s ; ...
An Adaptive Color-Based ... 22页 免费 Auxiliary Variable Based... 20页... Particle Filter Based on... 暂无评价 4页 免费 Object tracking with an ...
Many Object Tracking with Self-Updating Tracking Window 3 existing tracking ... K., Koller-Meier E., Van Gool L.: An adaptive color-based particle ...
Key words moving detection; object tracking; color model; mean-shift 在...An adaptive color-based particle filter[J]. Image and Vision Computing, ...
Technology, Soochow University, Suzhou Jiangsu 215006, China) Abstract:This paper proposes an adaptive window object tracking method based on particle filter....
热门文档