RT Journal Article
JF IEEE Transactions on Visualization & Computer Graphics
YR 2009
VO 16
SP 355
TI Real-Time Detection and Tracking for Augmented Reality on Mobile Phones
A1 Dieter Schmalstieg,
A1 Tom Drummond,
A1 Alessandro Mulloni,
A1 Gerhard Reitmayr,
A1 Daniel Wagner,
K1 Information interfaces and presentation
K1 multimedia information systems
K1 artificial
K1 augmented
K1 and virtual realities
K1 image processing and computer vision
K1 scene analysis
K1 tracking.
AB In this paper, we present three techniques for 6DOF natural feature tracking in real time on mobile phones. We achieve interactive frame rates of up to 30 Hz for natural feature tracking from textured planar targets on current generation phones. We use an approach based on heavily modified state-of-the-art feature descriptors, namely SIFT and Ferns plus a template-matching-based tracker. While SIFT is known to be a strong, but computationally expensive feature descriptor, Ferns classification is fast, but requires large amounts of memory. This renders both original designs unsuitable for mobile phones. We give detailed descriptions on how we modified both approaches to make them suitable for mobile phones. The template-based tracker further increases the performance and robustness of the SIFT- and Ferns-based approaches. We present evaluations on robustness and performance and discuss their appropriateness for Augmented Reality applications.
PB IEEE Computer Society, [URL:http://www.computer.org]
SN 1077-2626
LA English
DO 10.1109/TVCG.2009.99
LK http://doi.ieeecomputersociety.org/10.1109/TVCG.2009.99