Real-time tracking for virtual environments using scaat kalman filtering and unsynchronised cameras

Niels Tjørnly Rasmussen, Morritz Störring, Thomas B. Moeslund, Erik Granum

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

5 Citations (Scopus)

Abstract

This paper presents a real-time outside-in camera-based tracking system for wireless 3D pose tracking of a user’s head and hand in a virtual environment. The system uses four unsynchronised cameras as sensors and passive retroreflective markers arranged in rigid bodies as targets. In order to achieve high update rates and to cope with the unsynchronised data a single-constraint-at-a-time (SCAAT) Extended Kalman Filtering approach is used that recursively integrates measurements as soon as they are available one-at-a-time. Tests show that this approach is more robust to occlusions and provides less noisy pose estimates with a higher update rate than a conventional stereo triangulation approach.
Original languageEnglish
Title of host publicationVISAPP 2006 : Proceedings of the First International Conference on Computer Vision Theory and Applications
Number of pages8
PublisherInstitute for Systems and Technologies of Information, Control and Communication
Publication date2006
Pages333-341
ISBN (Print)9728865406
Publication statusPublished - 2006
EventInternational conference on computer vision theory and applications - SETÚBAL, Portugal
Duration: 25 Feb 200628 Feb 2006
Conference number: 1

Conference

ConferenceInternational conference on computer vision theory and applications
Number1
CountryPortugal
CitySETÚBAL
Period25/02/200628/02/2006

Fingerprint

Virtual reality
Cameras
Triangulation
Sensors

Keywords

  • Tracking
  • SCAAT Extended Kalman Filter
  • Pose Estimation
  • Stereo Triangulation

Cite this

Rasmussen, N. T., Störring, M., Moeslund, T. B., & Granum, E. (2006). Real-time tracking for virtual environments using scaat kalman filtering and unsynchronised cameras. In VISAPP 2006: Proceedings of the First International Conference on Computer Vision Theory and Applications (pp. 333-341). Institute for Systems and Technologies of Information, Control and Communication.
Rasmussen, Niels Tjørnly ; Störring, Morritz ; Moeslund, Thomas B. ; Granum, Erik. / Real-time tracking for virtual environments using scaat kalman filtering and unsynchronised cameras. VISAPP 2006: Proceedings of the First International Conference on Computer Vision Theory and Applications. Institute for Systems and Technologies of Information, Control and Communication, 2006. pp. 333-341
@inproceedings{e7b69c4089d711dbbb3d000ea68e967b,
title = "Real-time tracking for virtual environments using scaat kalman filtering and unsynchronised cameras",
abstract = "This paper presents a real-time outside-in camera-based tracking system for wireless 3D pose tracking of a user’s head and hand in a virtual environment. The system uses four unsynchronised cameras as sensors and passive retroreflective markers arranged in rigid bodies as targets. In order to achieve high update rates and to cope with the unsynchronised data a single-constraint-at-a-time (SCAAT) Extended Kalman Filtering approach is used that recursively integrates measurements as soon as they are available one-at-a-time. Tests show that this approach is more robust to occlusions and provides less noisy pose estimates with a higher update rate than a conventional stereo triangulation approach.",
keywords = "Tracking, SCAAT Extended Kalman Filter, Pose Estimation, Stereo Triangulation",
author = "Rasmussen, {Niels Tj{\o}rnly} and Morritz St{\"o}rring and Moeslund, {Thomas B.} and Erik Granum",
year = "2006",
language = "English",
isbn = "9728865406",
pages = "333--341",
booktitle = "VISAPP 2006",
publisher = "Institute for Systems and Technologies of Information, Control and Communication",

}

Rasmussen, NT, Störring, M, Moeslund, TB & Granum, E 2006, Real-time tracking for virtual environments using scaat kalman filtering and unsynchronised cameras. in VISAPP 2006: Proceedings of the First International Conference on Computer Vision Theory and Applications. Institute for Systems and Technologies of Information, Control and Communication, pp. 333-341, SETÚBAL, Portugal, 25/02/2006.

Real-time tracking for virtual environments using scaat kalman filtering and unsynchronised cameras. / Rasmussen, Niels Tjørnly; Störring, Morritz; Moeslund, Thomas B.; Granum, Erik.

VISAPP 2006: Proceedings of the First International Conference on Computer Vision Theory and Applications. Institute for Systems and Technologies of Information, Control and Communication, 2006. p. 333-341.

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

TY - GEN

T1 - Real-time tracking for virtual environments using scaat kalman filtering and unsynchronised cameras

AU - Rasmussen, Niels Tjørnly

AU - Störring, Morritz

AU - Moeslund, Thomas B.

AU - Granum, Erik

PY - 2006

Y1 - 2006

N2 - This paper presents a real-time outside-in camera-based tracking system for wireless 3D pose tracking of a user’s head and hand in a virtual environment. The system uses four unsynchronised cameras as sensors and passive retroreflective markers arranged in rigid bodies as targets. In order to achieve high update rates and to cope with the unsynchronised data a single-constraint-at-a-time (SCAAT) Extended Kalman Filtering approach is used that recursively integrates measurements as soon as they are available one-at-a-time. Tests show that this approach is more robust to occlusions and provides less noisy pose estimates with a higher update rate than a conventional stereo triangulation approach.

AB - This paper presents a real-time outside-in camera-based tracking system for wireless 3D pose tracking of a user’s head and hand in a virtual environment. The system uses four unsynchronised cameras as sensors and passive retroreflective markers arranged in rigid bodies as targets. In order to achieve high update rates and to cope with the unsynchronised data a single-constraint-at-a-time (SCAAT) Extended Kalman Filtering approach is used that recursively integrates measurements as soon as they are available one-at-a-time. Tests show that this approach is more robust to occlusions and provides less noisy pose estimates with a higher update rate than a conventional stereo triangulation approach.

KW - Tracking

KW - SCAAT Extended Kalman Filter

KW - Pose Estimation

KW - Stereo Triangulation

M3 - Article in proceeding

SN - 9728865406

SP - 333

EP - 341

BT - VISAPP 2006

PB - Institute for Systems and Technologies of Information, Control and Communication

ER -

Rasmussen NT, Störring M, Moeslund TB, Granum E. Real-time tracking for virtual environments using scaat kalman filtering and unsynchronised cameras. In VISAPP 2006: Proceedings of the First International Conference on Computer Vision Theory and Applications. Institute for Systems and Technologies of Information, Control and Communication. 2006. p. 333-341