Show simple item record

dc.contributor.advisorEnsor, Andrew
dc.contributor.advisorHall, Seth
dc.contributor.authorDa Fonseca, Eleanor
dc.date.accessioned2015-07-09T03:54:45Z
dc.date.available2015-07-09T03:54:45Z
dc.date.copyright2015
dc.date.created2015
dc.identifier.urihttp://hdl.handle.net/10292/8933
dc.description.abstractColourFAST is an alternative technique to FAST developed by Ensor and Hall used to extract feature point descriptors from an image based on colour change values. The extracted descriptor is compact and, therefore, efficient to compute and match. The purpose of this thesis is to extend the Colour-FAST feature descriptor from a 4-dimensional vector to a 6-dimensional vector to improve feature point matching accuracy. This is achieved by incorporating spatial locality to gain a sense of the shape of an object alongside its colour change information. The main focus is designing, developing and testing feature point matching algorithms specifically architected for the GPU pipeline with an emphasis on accuracy while maintaining high throughput.en_NZ
dc.language.isoenen_NZ
dc.publisherAuckland University of Technology
dc.subjectGPUen_NZ
dc.subjectGPU-accelerationen_NZ
dc.subjectColourFASTen_NZ
dc.subjectObject recognitionen_NZ
dc.subjectSpatial localityen_NZ
dc.subjectEleanor Da Fonsecaen_NZ
dc.subjectSeth Hallen_NZ
dc.subjectAndrew Ensoren_NZ
dc.subjectFeature matchingen_NZ
dc.subjectComputer visionen_NZ
dc.subjectParallel computingen_NZ
dc.subjectGPGPUen_NZ
dc.titleUtilizing spatial locality of ColourFAST features for GPU-Accelerated object recognitionen_NZ
dc.typeThesis
thesis.degree.grantorAuckland University of Technology
thesis.degree.grantorAuckland University of Technology
thesis.degree.levelMasters Theses
thesis.degree.nameMaster of Scienceen_NZ
thesis.degree.discipline
dc.rights.accessrightsOpenAccess
dc.date.updated2015-07-09T03:07:39Z


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record