DMCA
Going out: Robust modelbased tracking for outdoor augmented reality (2006)
| Venue: | Proceedings of 5th IEEE and ACM International Symposium on Mixed and Augmented Reality (ISMAR |
| Citations: | 66 - 3 self |
BibTeX
@INPROCEEDINGS{Reitmayr06goingout:,
author = {Gerhard Reitmayr and Tom W. Drummond},
title = {Going out: Robust modelbased tracking for outdoor augmented reality},
booktitle = {Proceedings of 5th IEEE and ACM International Symposium on Mixed and Augmented Reality (ISMAR},
year = {2006},
pages = {109--118}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Figure 1: (Left) A user operating a handheld augmented reality unit tracked in an urban environment. (Middle) Live shot showing the unit tracking a building. (Right) Screenshot from a pose close to the left images with overlaid building outline. This paper presents a model-based hybrid tracking system for outdoor augmented reality in urban environments enabling accurate, realtime overlays for a handheld device. The system combines several well-known approaches to provide a robust experience that surpasses each of the individual components alone: an edge-based tracker for accurate localisation, gyroscope measurements to deal with fast motions, measurements of gravity and magnetic field to avoid drift, and a back store of reference frames with online frame selection to re-initialise automatically after dynamic occlusions or failures. A novel edge-based tracker dispenses with the conventional edge model, and uses instead a coarse, but textured, 3D model. This yields several advantages: scale-based detail culling is automatic, appearance-based edge signatures can be used to improve matching and the models needed are more commonly available. The accuracy and robustness of the resulting system is demonstrated with comparisons to map-based ground truth data.
Keyphrases
urban environment magnetic field dynamic occlusion live shot map-based ground truth data fast motion scale-based detail culling gyroscope measurement robust experience overlaid building outline edge-based tracker several well-known approach pose close novel edge-based tracker conventional edge model reference frame reality unit accurate localisation back store model-based hybrid tracking system appearance-based edge signature handheld device online frame selection individual component several advantage realtime overlay
