University of Canterbury Home
    • Admin
    UC Research Repository
    UC Library
    JavaScript is disabled for your browser. Some features of this site may not work without it.
    View Item 
    1. UC Home
    2. Library
    3. UC Research Repository
    4. Faculty of Engineering | Te Kaupeka Pūhanga
    5. Engineering: Theses and Dissertations
    6. View Item
    1. UC Home
    2.  > 
    3. Library
    4.  > 
    5. UC Research Repository
    6.  > 
    7. Faculty of Engineering | Te Kaupeka Pūhanga
    8.  > 
    9. Engineering: Theses and Dissertations
    10.  > 
    11. View Item

    Real-Time Hybrid Tracking for Outdoor Augmented Reality (2014)

    Thumbnail
    View/Open
    thesis_fulltext.pdf (29.50Mb)
    Williams_Use_of_thesis_form.pdf (128.9Kb)
    Type of Content
    Theses / Dissertations
    UC Permalink
    http://hdl.handle.net/10092/9188
    http://dx.doi.org/10.26021/7184
    
    Thesis Discipline
    Computer Science
    Degree Name
    Master of Science
    Publisher
    University of Canterbury. Computer Science and Software Engineering
    Collections
    • Engineering: Theses and Dissertations [2892]
    Authors
    Williams, Samuel Grant Dawson
    show all
    Abstract

    Outdoor tracking and registration are important enabling technologies for mobile augmented reality. Sensor fusion and image processing can be used to improve global tracking and registration for low-cost mobile devices with limited computational power and sensor accuracy. Prior research has confirmed the benefits of this approach with high-end hardware, however the methods previously used are not ideal for current consumer mobile devices. We discuss the development of a hybrid tracking and registration algorithm that combines multiple sensors and image processing to improve on existing work in both performance and accuracy. As part of this, we developed the Transform Flow toolkit, which is one of the first open source systems for developing and quantifiably evaluating mobile AR tracking algorithms. We used this system to compare our proposed hybrid tracking algorithm with a purely sensor based approach, and to perform a user study to analyse the effects of improved precision on real world tracking tasks. Our results show that our implementation is an improvement over a purely sensor fusion based approach; accuracy is improved up to 25x in some cases with only 2-4ms additional processing per frame, in comparison with other algorithms which can take over 300ms.

    Keywords
    Mobile; Augmented Reality; Outdoor; Tracking; Registration; Computer Vision
    Rights
    Copyright Samuel Grant Dawson Williams
    https://canterbury.libguides.com/rights/theses

    Related items

    Showing items related by title, author, creator and subject.

    • Real-time Visual Representations for Mixed Reality Remote Collaboration 

      Gao L; Bai H; Piumsomboon T; Lee G; Lindeman RW; Billinghurst, Mark (2017)
      We present a prototype Mixed Reality (MR) system with a hybrid interface to support remote collaboration between a local worker and a remote expert in a large-scale work space. By combining a low-resolution 3D point-cloud ...
    • Colour Tracking for Unintrusive Real-Time Human Motion Capture to Drive an Avatar 

      Grant, Robert (University of Canterbury, 2004)
      This report presents two colour tracking techniques developed for use in a real-time interactive motion capture system. The aim of these trackers is to remove the need for special clothing and markers in these systems. ...
    • Real-Time Quantitative Analysis and Surface Registration of Medical Scan Data 

      Bentley, Richard (University of Canterbury, 1993)
      Several medical scanning techniques provide data about a volume that is being scanned in a series of slices. The term volume refers to some object of interest being scanned, usually a closed three-dimensional object. ...
    Advanced Search

    Browse

    All of the RepositoryCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThesis DisciplineThis CollectionBy Issue DateAuthorsTitlesSubjectsThesis Discipline

    Statistics

    View Usage Statistics
    • SUBMISSIONS
    • Research Outputs
    • UC Theses
    • CONTACTS
    • Send Feedback
    • +64 3 369 3853
    • ucresearchrepository@canterbury.ac.nz
    • ABOUT
    • UC Research Repository Guide
    • Copyright and Disclaimer
    • SUBMISSIONS
    • Research Outputs
    • UC Theses
    • CONTACTS
    • Send Feedback
    • +64 3 369 3853
    • ucresearchrepository@canterbury.ac.nz
    • ABOUT
    • UC Research Repository Guide
    • Copyright and Disclaimer