Markerless tracking algorithm based on 3d model for augmented reality system

Authors:
Peng Yao;Can Chen;Dongdong Weng
Affiliations:
School of Optoelectronics, Beijing Institute of Technology, Beijing, China,Science and Technology on Complex Land Systems Simulation Laboratory, Beijing, China;School of Optoelectronics, Beijing Institute of Technology, Beijing, China;School of Optoelectronics, Beijing Institute of Technology, Beijing, China
Venue:
IScIDE'12 Proceedings of the third Sino-foreign-interchange conference on Intelligent Science and Intelligent Data Engineering
Year:
2012

Citing 10
Cited 0

Recent Advances in Augmented Reality

IEEE Computer Graphics and Applications
Pose Estimation for Planar Structures

IEEE Computer Graphics and Applications
Shape Indexing Using Approximate Nearest-Neighbour Search in High-Dimensional Spaces

CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Object Recognition from Local Scale-Invariant Features

ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
Online 6 DOF Augmented Reality Registration from Natural Features

ISMAR '02 Proceedings of the 1st International Symposium on Mixed and Augmented Reality
Multiple View Geometry in Computer Vision

Multiple View Geometry in Computer Vision
Robust Visual Tracking for Non-Instrumented Augmented Reality

ISMAR '03 Proceedings of the 2nd IEEE/ACM International Symposium on Mixed and Augmented Reality
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
Stable Real-Time 3D Tracking Using Online and Offline Information

IEEE Transactions on Pattern Analysis and Machine Intelligence
Monocular model-based 3D tracking of rigid objects

Foundations and Trends® in Computer Graphics and Vision

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a markerless augmented reality(AR) system based on 3D model. First, the feature of environment was extracted using SIFT operator, then the method of stratified reconstruction was used to reconstruct the 3D scene, after that we constructed the database of prior knowledge using the KD-Tree. Finally, we tracked the 3D model based on these prior knowledge via feature matching and pose estimation in real time. Experimental results demonstrated that this method is sufficient for markerless tracking registration. With the prior knowledge, key frame selection problem can be avoided and the running speed is also increased.