A plane tracker for AEC-automation applications

Chen Feng, Vineet R. Kamat

Research output: Contribution to conferencePaper

Abstract

Purpose: We propose a new registration algorithm and computing framework, the keg tracker, for estimating a camera's position and orientation for a general class of mobile context-aware applications in architecture, engineering, and construction (AEC). Method: By studying two classic types of natural marker-based registration algorithms, homography-from-detection and homography-from-tracking, and overcoming their specific limitations of jitter and drift, our method applies two global constraints (geometric and appearance) to prevent tracking errors from propagating between consecutive frames. Results & Discussion: The proposed method is able to achieve an increase in both stability and accuracy, while being fast enough for real-time applications. Experiments on both synthesized and real world test cases demonstrate that our method is superior to existing state-of-the-art registration algorithms. The paper also explores several AEC-applications of our method in context-aware computing and desktop augmented reality.

Original languageEnglish (US)
StatePublished - Dec 1 2012
Event29th International Symposium of Automation and Robotics in Construction, ISARC 2012 - Eindhoven, Netherlands
Duration: Jun 26 2012Jun 29 2012

Other

Other29th International Symposium of Automation and Robotics in Construction, ISARC 2012
CountryNetherlands
CityEindhoven
Period6/26/126/29/12

Fingerprint

Automation
Engineering
Registration
Homography
Augmented reality
Jitter
Context-aware Computing
Cameras
Global Constraints
Augmented Reality
Context-aware
Consecutive
Camera
Architecture
Real-time
Experiments
Computing
Demonstrate
Experiment

Keywords

  • AR registration
  • Context-aware computing
  • Information technology
  • Tracking

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Building and Construction
  • Modeling and Simulation

Cite this

Feng, C., & Kamat, V. R. (2012). A plane tracker for AEC-automation applications. Paper presented at 29th International Symposium of Automation and Robotics in Construction, ISARC 2012, Eindhoven, Netherlands.

A plane tracker for AEC-automation applications. / Feng, Chen; Kamat, Vineet R.

2012. Paper presented at 29th International Symposium of Automation and Robotics in Construction, ISARC 2012, Eindhoven, Netherlands.

Research output: Contribution to conferencePaper

Feng, C & Kamat, VR 2012, 'A plane tracker for AEC-automation applications', Paper presented at 29th International Symposium of Automation and Robotics in Construction, ISARC 2012, Eindhoven, Netherlands, 6/26/12 - 6/29/12.
Feng C, Kamat VR. A plane tracker for AEC-automation applications. 2012. Paper presented at 29th International Symposium of Automation and Robotics in Construction, ISARC 2012, Eindhoven, Netherlands.
Feng, Chen ; Kamat, Vineet R. / A plane tracker for AEC-automation applications. Paper presented at 29th International Symposium of Automation and Robotics in Construction, ISARC 2012, Eindhoven, Netherlands.
@conference{b1849da77ce34f79b66472ff4b6e47db,
title = "A plane tracker for AEC-automation applications",
abstract = "Purpose: We propose a new registration algorithm and computing framework, the keg tracker, for estimating a camera's position and orientation for a general class of mobile context-aware applications in architecture, engineering, and construction (AEC). Method: By studying two classic types of natural marker-based registration algorithms, homography-from-detection and homography-from-tracking, and overcoming their specific limitations of jitter and drift, our method applies two global constraints (geometric and appearance) to prevent tracking errors from propagating between consecutive frames. Results & Discussion: The proposed method is able to achieve an increase in both stability and accuracy, while being fast enough for real-time applications. Experiments on both synthesized and real world test cases demonstrate that our method is superior to existing state-of-the-art registration algorithms. The paper also explores several AEC-applications of our method in context-aware computing and desktop augmented reality.",
keywords = "AR registration, Context-aware computing, Information technology, Tracking",
author = "Chen Feng and Kamat, {Vineet R.}",
year = "2012",
month = "12",
day = "1",
language = "English (US)",
note = "29th International Symposium of Automation and Robotics in Construction, ISARC 2012 ; Conference date: 26-06-2012 Through 29-06-2012",

}

TY - CONF

T1 - A plane tracker for AEC-automation applications

AU - Feng, Chen

AU - Kamat, Vineet R.

PY - 2012/12/1

Y1 - 2012/12/1

N2 - Purpose: We propose a new registration algorithm and computing framework, the keg tracker, for estimating a camera's position and orientation for a general class of mobile context-aware applications in architecture, engineering, and construction (AEC). Method: By studying two classic types of natural marker-based registration algorithms, homography-from-detection and homography-from-tracking, and overcoming their specific limitations of jitter and drift, our method applies two global constraints (geometric and appearance) to prevent tracking errors from propagating between consecutive frames. Results & Discussion: The proposed method is able to achieve an increase in both stability and accuracy, while being fast enough for real-time applications. Experiments on both synthesized and real world test cases demonstrate that our method is superior to existing state-of-the-art registration algorithms. The paper also explores several AEC-applications of our method in context-aware computing and desktop augmented reality.

AB - Purpose: We propose a new registration algorithm and computing framework, the keg tracker, for estimating a camera's position and orientation for a general class of mobile context-aware applications in architecture, engineering, and construction (AEC). Method: By studying two classic types of natural marker-based registration algorithms, homography-from-detection and homography-from-tracking, and overcoming their specific limitations of jitter and drift, our method applies two global constraints (geometric and appearance) to prevent tracking errors from propagating between consecutive frames. Results & Discussion: The proposed method is able to achieve an increase in both stability and accuracy, while being fast enough for real-time applications. Experiments on both synthesized and real world test cases demonstrate that our method is superior to existing state-of-the-art registration algorithms. The paper also explores several AEC-applications of our method in context-aware computing and desktop augmented reality.

KW - AR registration

KW - Context-aware computing

KW - Information technology

KW - Tracking

UR - http://www.scopus.com/inward/record.url?scp=84893248883&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84893248883&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:84893248883

ER -