Applying deep learning in augmented reality tracking
Date
2016-11-12
Authors
Editor(s)
Advisor
Supervisor
Co-Advisor
Co-Supervisor
Instructor
BUIR Usage Stats
3
views
views
87
downloads
downloads
Citation Stats
Attention Stats
Series
Abstract
An existing deep learning architecture has been adapted to solve the detection problem in camera-based tracking for augmented reality (AR). A known target, in this case a planar object, is rendered under various viewing conditions including varying orientation, scale, illumination and sensor noise. The resulting corpus is used to train a convolutional neural network to match given patches in an incoming image. The results show comparable or better performance compared to state of art methods. Timing performance of the detector needs improvement but when considered in conjunction with the robust pose estimation process promising results are shown. © 2016 IEEE.
Source Title
Proceedings - 12th International Conference on Signal Image Technology and Internet-Based Systems, SITIS 2016
Publisher
IEEE
Course
Other identifiers
Book Title
Degree Discipline
Degree Level
Degree Name
Citation
Permalink
Published Version (Please cite this version)
Language
English