資源描述：
《visual object tracking based on mean-shift and particle-kalman filter視覺(jué)物體跟蹤基于均值漂移和particle-kalman過(guò)濾器》由會(huì)員上傳分享，免費(fèi)在線閱讀，更多相關(guān)內(nèi)容在學(xué)術(shù)論文-天天文庫(kù)。
1、碩士留學(xué)生學(xué)位論文VisualObjectTrackingBasedonMean-shiftandParticleandandPPartP-KalmanFilter作者姓名IreneAnindaputriIswanto學(xué)科專業(yè)ElectricalandComputerEngineering指導(dǎo)教師李彬副教授所在學(xué)院AutomationScienceAndEngineering論文提交日期2016年5月23日VisualObjectTrackingBasedonMean-shiftandParticle-KalmanFilterADissertationSubmi
2、ttedfortheDegreeofMasterCandidate：IreneAnindaputriIswantoSupervisor：AssociateProfessorBinLiSouthChinaUniversityofTechnologyGuangzhou,China分類號(hào)：學(xué)校代號(hào)：10561學(xué)號(hào)：201422800063華南理工大學(xué)碩士學(xué)位論文VisualObjectTrackingBasedonMean-shiftandParticle-KalmanFilter作者姓名：IreneAnindaputriIswanto指導(dǎo)教師姓名、職稱：李彬，副教授
3、申請(qǐng)學(xué)位級(jí)別：工程碩士學(xué)科專業(yè)名稱：電氣與計(jì)算機(jī)程研究方向：圖像處理論文提交日期：2016年05月23日論文答辯日期：2016年06月08日學(xué)位授予單位：華南理工大學(xué)學(xué)位授予日期：2016年06月25日答辯委員會(huì)成員：主席：LUGUONENGG委員：裴海龍，蘇為洲，李向陽(yáng)，李彬gABSTRACTDuetotheincreasingofvideosurveillancesystemrequirements,Intelligentvideosurveillancesystemhasbecomechallengingtopicincomputervisionresea
4、rchfield.Therearefourkeystepsinintelligentvideosurveillancesystem,i.e.objectdetection,objectclassification,objecttracking,andobjectanalysis.Amongthesesteps,objecttrackingisconsideredascrucialandsignificanttaskinintelligentvideosurveillancesystem.Objecttrackingisconsideredasdifficultt
5、askbecauseofseveralproblemssuchasilluminationvariation,trackingnon-rigidobject,non-linearmotion,occlusion,andrequirementofrealtimeimplementation.Thereforeitisnecessarytobuildavisualobjecttrackingalgorithmwhichcanovercometheseproblems.Everysinglealgorithminvisualobjecttrackingalwaysha
6、sbothstrengthsanddrawbacks.Therefore,utilizingonlyonesinglealgorithmfortrackingusuallyisconsideredasinefficientbecauseeverysinglealgorithmhaslimitations.Basedonthisreason,inthisthesisatrackingalgorithmwhichcombinesmean-shiftandparticle-Kalmanfilterisproposed.Intheproposedmethod,mean-
7、shiftisusedasmastertrackerwhenthetargetobjectisnotoccluded.Whenocclusionisoccurredorthemean-shifttrackingresultisnotconvincing,particle-Kalmanfilterwillactasmastertrackertoimprovethetrackingresults.Experimentalshowsthattheproposedmethodcanworkwellindealingwithtrackingproblemssuchasno
8、n-rigidobjec
