Title
Markerless Tracking Using Polar Correlation Of Camera Optical Flow
Keywords
I.4.9 [image processing and computer vision]: scene analysis - motion, tracking; Markerless; Multi camera; Optical flow; Polar correlation
Abstract
We present a novel, real-time, markerless vision-based tracking system, employing a rigid orthogonal configuration of two pairs of opposing cameras. Our system uses optical flow over sparse features to overcome the limitation of vision-based systems that require markers or a pre-loaded model of the physical environment. We show how opposing cameras enable cancellation of common components of optical flow leading to an efficient tracking algorithm. Experiments comparing our device with an electromagnetic tracker show that its average tracking accuracy is 80% over 185 frames, and it is able to track large range motions even in outdoor settings. ©2010 IEEE.
Publication Date
5-31-2010
Publication Title
Proceedings - IEEE Virtual Reality
Number of Pages
223-226
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1109/VR.2010.5444784
Copyright Status
Unknown
Socpus ID
77952699666 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/77952699666
STARS Citation
Gupta, Prince; Lobo, Niels Da Vitoria; and Laviola, Joseph J., "Markerless Tracking Using Polar Correlation Of Camera Optical Flow" (2010). Scopus Export 2010-2014. 1108.
https://stars.library.ucf.edu/scopus2010/1108