Robust Pose Estimation for Outdoor Mixed Reality with Sensor Fusion

Authors:
Zhiying Zhou;Jayashree Karlekar;Daniel Hii;Miriam Schneider;Weiquan Lu;Stephen Wittkopf
Affiliations:
Interactive Multimedia Lab, Department of Electrical Computer Engineering, Department of Architecture, National University of Singapore, Singapore;Interactive Multimedia Lab, Department of Electrical Computer Engineering, Department of Architecture, National University of Singapore, Singapore;Interactive Multimedia Lab, Department of Electrical Computer Engineering, Department of Architecture, National University of Singapore, Singapore;Interactive Multimedia Lab, Department of Electrical Computer Engineering, Department of Architecture, National University of Singapore, Singapore;Interactive Multimedia Lab, Department of Electrical Computer Engineering, Department of Architecture, National University of Singapore, Singapore;Interactive Multimedia Lab, Department of Electrical Computer Engineering, Department of Architecture, National University of Singapore, Singapore
Venue:
UAHCI '09 Proceedings of the 5th International Conference on Universal Access in Human-Computer Interaction. Part III: Applications and Services
Year:
2009

Citing 7
Cited 0

A Maximum Likelihood Framework for Determining Moving Edges

IEEE Transactions on Pattern Analysis and Machine Intelligence
Recent Advances in Augmented Reality

IEEE Computer Graphics and Applications
Fusion of Vision and Gyro Tracking for Robust Augmented Reality Registration

VR '01 Proceedings of the Virtual Reality 2001 Conference (VR'01)
A Touring Machine: Prototyping 3D Mobile Augmented Reality Systems for Exploring the Urban Environment

ISWC '97 Proceedings of the 1st IEEE International Symposium on Wearable Computers
A Robust Hybrid Tracking System for Outdoor Augmented Reality

VR '04 Proceedings of the IEEE Virtual Reality 2004
Monocular model-based 3D tracking of rigid objects

Foundations and Trends® in Computer Graphics and Vision
Going out: robust model-based tracking for outdoor augmented reality

ISMAR '06 Proceedings of the 5th IEEE and ACM International Symposium on Mixed and Augmented Reality

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a sensor fusion based technique for outdoor augmented reality system for mobile devices using GPS, gyroscope, and geo-referenced 3D models of the urban environment. Geo-spatial interaction not only provides overlays of the existing environment but compliments with other data such as location-specific photos, videos and other information from different time periods enhancing the overall user experience of augmented reality. To provide robust pose estimation of the camera relative to the world coordinates, firstly, GPS and gyroscope are used to obtain the rough estimation. Secondly, model based silhouette tracking and sensor fusion approach is used to refine the rough estimation and to provide seamless media rich augmentation of 3D textured models.