This Is AuburnElectronic Theses and Dissertations

Show simple item record

Registration and Tracking of Objects with Computer Vision for Autonomous Vehicles


Metadata FieldValueLanguage
dc.contributor.advisorHodel, A. Scottedward
dc.contributor.advisorBevly, David
dc.contributor.authorNevin, Andrew
dc.date.accessioned2009-04-15T15:44:42Z
dc.date.available2009-04-15T15:44:42Z
dc.date.issued2009-04-15T15:44:42Z
dc.identifier.urihttp://hdl.handle.net/10415/1633
dc.description.abstractFor this research, an autonomous leader-follower vehicle caravan is being designed using computer vision. The focus of this research is to investigate computer vision methods of identifying objects detected by the leader vehicle and determining the follower vehicle' s position relative to the objects. Many object registration and tracking methods are presented in this paper such as Hough transforms, optical flow, and normalized cross correlation. A novel statistical-gradient method is presented to combine feature based methods and area based methods for object registration and tracking. These methods are evaluated against both synthetic and captured video data. This registration method is shown to be effective with both synthetic data and acquired data.en
dc.rightsEMBARGO_NOT_AUBURNen
dc.subjectElectrical Engineeringen
dc.titleRegistration and Tracking of Objects with Computer Vision for Autonomous Vehiclesen
dc.typethesisen
dc.embargo.lengthNO_RESTRICTIONen_US
dc.embargo.statusNOT_EMBARGOEDen_US

Files in this item

Show simple item record