Augmented reality registration algorithm based on nature feature recognition

Jing Chen; Yong Tian Wang; Jun Wei Guo; Wei Liu; Jing Dun Lin; Kang Xue; Yue Liu; Gang Yi Ding

doi:10.1007/s11432-010-4026-5

Augmented reality registration algorithm based on nature feature recognition

Jing Chen^*, Yong Tian Wang, Jun Wei Guo, Wei Liu, Jing Dun Lin, Kang Xue, Yue Liu, Gang Yi Ding

^*Corresponding author for this work

Beijing Institute of Technology

Research output: Contribution to journal › Article › peer-review

6 Citations (Scopus)

Abstract

This paper presents an improved key frame based augmented reality registration algorithm for real-time motion tracking in outdoor environment. In such applications, wide-baseline feature matching is a critical problem. In this paper, we apply randomized tree method to match key points extracted from the input image to those key frames as a classification problem. Extended Kalman filter is also utilized for jitter correction. A video see-through mobile augmented reality system is built for the on-site digital reconstruction of Yuanmingyuan Garden. Experimental results demonstrate that this algorithm is real-time, robust and effective for outdoor tracking.

Original language	English
Pages (from-to)	1555-1565
Number of pages	11
Journal	Science in China, Series F: Information Sciences
Volume	53
Issue number	8
DOIs	https://doi.org/10.1007/s11432-010-4026-5
Publication status	Published - 2010

Keywords

Camera tracking
Outdoor augmented reality
Randomized tree

Access to Document

10.1007/s11432-010-4026-5

Cite this

Chen, J., Wang, Y. T., Guo, J. W., Liu, W., Lin, J. D., Xue, K., Liu, Y., & Ding, G. Y. (2010). Augmented reality registration algorithm based on nature feature recognition. Science in China, Series F: Information Sciences, 53(8), 1555-1565. https://doi.org/10.1007/s11432-010-4026-5

@article{79f83e2a655d4b4284081955f6dc31cc,

title = "Augmented reality registration algorithm based on nature feature recognition",

abstract = "This paper presents an improved key frame based augmented reality registration algorithm for real-time motion tracking in outdoor environment. In such applications, wide-baseline feature matching is a critical problem. In this paper, we apply randomized tree method to match key points extracted from the input image to those key frames as a classification problem. Extended Kalman filter is also utilized for jitter correction. A video see-through mobile augmented reality system is built for the on-site digital reconstruction of Yuanmingyuan Garden. Experimental results demonstrate that this algorithm is real-time, robust and effective for outdoor tracking.",

keywords = "Camera tracking, Outdoor augmented reality, Randomized tree",

author = "Jing Chen and Wang, {Yong Tian} and Guo, {Jun Wei} and Wei Liu and Lin, {Jing Dun} and Kang Xue and Yue Liu and Ding, {Gang Yi}",

year = "2010",

doi = "10.1007/s11432-010-4026-5",

language = "English",

volume = "53",

pages = "1555--1565",

journal = "Science in China, Series F: Information Sciences",

issn = "1009-2757",

publisher = "Science China Press",

number = "8",

}

TY - JOUR

T1 - Augmented reality registration algorithm based on nature feature recognition

AU - Chen, Jing

AU - Wang, Yong Tian

AU - Guo, Jun Wei

AU - Liu, Wei

AU - Lin, Jing Dun

AU - Xue, Kang

AU - Liu, Yue

AU - Ding, Gang Yi

PY - 2010

Y1 - 2010

N2 - This paper presents an improved key frame based augmented reality registration algorithm for real-time motion tracking in outdoor environment. In such applications, wide-baseline feature matching is a critical problem. In this paper, we apply randomized tree method to match key points extracted from the input image to those key frames as a classification problem. Extended Kalman filter is also utilized for jitter correction. A video see-through mobile augmented reality system is built for the on-site digital reconstruction of Yuanmingyuan Garden. Experimental results demonstrate that this algorithm is real-time, robust and effective for outdoor tracking.

AB - This paper presents an improved key frame based augmented reality registration algorithm for real-time motion tracking in outdoor environment. In such applications, wide-baseline feature matching is a critical problem. In this paper, we apply randomized tree method to match key points extracted from the input image to those key frames as a classification problem. Extended Kalman filter is also utilized for jitter correction. A video see-through mobile augmented reality system is built for the on-site digital reconstruction of Yuanmingyuan Garden. Experimental results demonstrate that this algorithm is real-time, robust and effective for outdoor tracking.

KW - Camera tracking

KW - Outdoor augmented reality

KW - Randomized tree

UR - http://www.scopus.com/inward/record.url?scp=77954428714&partnerID=8YFLogxK

U2 - 10.1007/s11432-010-4026-5

DO - 10.1007/s11432-010-4026-5

M3 - Article

AN - SCOPUS:77954428714

SN - 1009-2757

VL - 53

SP - 1555

EP - 1565

JO - Science in China, Series F: Information Sciences

JF - Science in China, Series F: Information Sciences

IS - 8

ER -

Augmented reality registration algorithm based on nature feature recognition

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this