MovingObjectDetectionforReal-TimeApplications
LuciaMaddalenaNationalResearchCouncilInstituteforHigh-PerformanceComputingandNetworking
ViaP.Castellino111,80131Naples,Italy
lucia.maddalena@na.icar.cnr.it
Abstract
Detectionofmovingobjectsinvideostreamsisthe rstrelevantstepofinformationextractioninmanycomputervisionapplications.Asidefromtheintrinsicusefulnessofbeingabletosegmentvideostreamsintomovingandback-groundcomponents,detectingmovingobjectsprovidesafo-cusofattentionforrecognition,classi cation,andactivityanalysis,makingtheselaterstepsmoreef cient.
Wepresentsomeextensionstothemethodformovingob-jectdetectionpresentedin[4].Ourmaincontributionsarerelatedtothepre-processingofintermediateresults(tran-siencemaps),aimedatenhancingtheaccuracyofdetec-tionresults,andtotheparallelizationofsomeofthemostcomputationallyintensivestepsusingSSE2instructions,inordertoenhanceef ciencyandallowforreal-timeapplica-tions.
1.Introduction
Detectionofmovingobjectsinvideostreamsisthe rstrelevantstepofinformationextractioninmanycomputervisionapplications,includingtraf cmonitoring,automatedremotevideosurveillance,andpeopletracking[3].Asidefromtheintrinsicusefulnessofbeingabletosegmentvideostreamsintomovingandbackgroundcomponents,detect-ingmovingobjectsprovidesafocusofattentionforrecog-nition,classi cation,andactivityanalysis,makingtheselaterstepsmoreef cient,sinceonlymovingpixelsneedbeconsidered[2].Theproblemisknowntobesigni cantanddif cult[8].Conventionalapproachestomovingobjectde-tectionincludetemporaldifferencing[7],backgroundsub-traction[8],andoptical ow[1].
Temporaldifferencingtakesintoaccountdifferencesinconsecutivesequenceframes,whichallowtodiscernstaticobjects(havingnulldifferences)frommovingobjects(hav-ingnon-nulldifferences).Thisapproachisveryadaptiveto
14th International Conference on Image Analysis and Processing (ICIAP 2007)

0-7695-2877-5/07 $25.00 © 2007
AlfredoPetrosino
UniversityofNaplesParthenopeDepartmentofAppliedScienceViaA.DeGasperi5,80133Naples,Italyalfredo.petrosino@uniparthenope.it
dynamicenvironments,butitisstrictlydependentontheve-locityofmovingobjectsinthesceneanditissubjecttotheforegroundapertureproblem.Incontrast,optical owtech-niquesaimatcomputinganapproximationtothe2Dmo-tion eld(projectionofthe3Dvelocitiesofsurfacepointsontotheimagingsurface)fromspatio-temporalpatternsofimageintensity[1].Theycanbeusedtodetectindepen-dentlymovingobjectsinthepresenceofcameramotion,butmostoptical owcomputationmethodsarecomputa-tionallycomplex,andcannotbeappliedtofull-framevideostreamsinreal-timewithoutspecializedhardware.
Surelybackgroundsubtractionisthemostcommonandef cientmethodtotackletheproblem(e.g.[6]).Itisbasedonthecomparisonofthecurrentsequenceframewithareferencebackground,includinginformationonthescenewithoutmovingobjects.Itisindependentonthevelocityofmovingobjectsanditisnotsubjecttotheforegroundaper-tureproblem,butitisextremelysensitivetodynamicscenechangesduetolightingandextraneousevents.Althoughtheseareusuallydetected,theyleavebehindholeswherethenewlyexposedbackgroundimagerydiffersfromtheknownbackgroundmodel(ghosts).Whilethebackgroundmodeleventuallyadaptstotheseholes,theygeneratefalsealarmsforashortperiodoftime.
Amongdifferentapproaches,theoneproposedin[4]al-lowsdisambiguationofmovingobjectsthatstopforawhile,areoccludedbyotherobjects,andthenresumemotion.Layereddetectionisbasedontwoprocesses:pixelanaly-sisandregionanalysis.Pixelanalysisdetermineswhetherapixelisstationaryortransientovertime,whileregionanalysisdetectsstationaryregionsofstationarypixelscor-respondingtostoppedobjects.Weadoptedthelayeredapproach,includingapre-processingoftransiencemapsaimedatsuppressingshadowsandreducingnoise,andclus-teringnon-backgroundpixelsusingregiongrowing.
Moreover,theneedforreal-timesystemsimposesverylowcomputationtimes.Wefocusedonmostcomputation-allyintensivestepsoftheproposedapproach,obtainingpar-
“嚣 GSM—MRF real.timemovingobjectdetection素PAN,Yi_junWUEngineering,zhe...andiswidelyusedvarietyofapplicationsofcomputervision,in— adaptiverelationship...
Amethod for real-time moving object detection is described. Anew ...For most applications, this can be considered to be real-time. 4. ...
(ICIIP 2011) A Novel Algorithm For Real Time Moving Object Tracking Sheikh...object detection and tracking methods are used for video coding applications....
Object-Oriented Real-Tim... 暂无评价 18页 免费 Moving Object Detection .... RTFrame An object-oriented application framework for real-time applications ...
REAL-TIME MOVING OBJECT DETECTION IN VIDEO SEQUENCES USING SPATIO-TEMPORAL ADAPTIVE GAUSSIAN MIXTURE MODELS Katharina Quast, Matthias Obermann and Andr? Kaup...
Moving Object Detection ... 6页 2财富值 REAL-TIME OBJECT DETECTI... 7页 1财富值 Algorithms for Real-Time... 暂无评价 30页 1财富值 A generative ...
Moving Object Detection ... 6页 2财富值 Switched Real-Time Commu... ... 1 Introduction Spectral Texturing for Real-Time Applications In this sketch ...
a smart visual surveillance system with real-time moving object detection, ...algorithms would lead to breakthroughs in applications that use visual ...
Moving Object Detection ... 6页 2财富值 Switched Real-Time Commu... ... Incremental Generation for Real{Time Applications Anne Kilger and Wolfgang ...
Robust real-time object detection_IT/计算机_专业资料。今日推荐 ... Real Time Robust Human... 8页 免费 Real-time moving objec... 6页 ...
热门文档