Implementation of mixed reality tracking algorithms on mobile clients
No Thumbnail Available
Journal Title
Journal ISSN
Volume Title
School of Electrical Engineering |
Master's thesis
Checking the digitized thesis and permission for publishing
Instructions for the author
Instructions for the author
Author
Date
2010
Department
Major/Subject
Signaalinkäsittelytekniikka
Mcode
S-88
Degree programme
Language
en
Pages
viii + 85 s. + liitt. 51
Series
Abstract
This thesis documents the design and implementation of two mixed reality tracking components: a gyroscope and a natural marker tracker. Both use RIFF (Rotation Invariant Fast Feature) descriptors for their object recognition needs. The Visual Gyroscope tracks the orientation of a mobile phone based on frames from its camera. The Natural Marker Tracker library is capable of creating, recognizing and tracking arbitrary markers. In both cases, a successful real-time implementation was created for an N900. The Natural Marker Tracker, however, would still require some work in order to be able to calculate 3D marker projections as it currently is only capable of calculating a 2D affine transformation.Description
Supervisor
Richter, AndreasThesis advisor
Kähäri, MarkusKeywords
mixed reality, augmented reality, natural marker, recognition, tracking, visual gyroscope, mobile, rotation invariant fast feature
