Home / Issues / 15.2018 / Position Estimation and Calibration of Inertial Motion Capture Systems Using Single Camera
Document Actions

VISIGRAPP 2018

Position Estimation and Calibration of Inertial Motion Capture Systems Using Single Camera

  1. Martin Madaras Institute of Software Technology and Interactive Systems, University of Technology, Vienna, Austria
  2. Adam Riečický Department of Applied Informatics, Comenius University, Bratislava, Slovakia
  3. Michal Mesároš Skeletex Research, Bratislava, Slovakia
  4. Michal Piovarči Saarland University, MMCI, Saarbrücken, Germany
  5. Roman Ďurikovič Department of Applied Informatics, Comenius University, Bratislava, Slovakia

Abstract

The paper proposes a hybrid system for position estimation of a motion capture suit and gloves as well as a method for an automatic skeleton calibration for motion capture gloves. The skeleton calibration works with a single image scan of the hand where the skeleton is fitted. The position estimation is based on a synchronization of an inertial motion capture system and a single camera optical setup. The proposed synchronization uses an iterative optimization of an energy potential in image space, minimizing the error between the camera image and a rendered virtual representation of the scene. For each frame, an input skeleton pose from the mocap suit is used to render a silhouette of a subject. Moreover, the local neighborhood around the last known position is searched by matching the silhouette to the distance transform representation of the camera image based on Chamfer matching. Using the combination of the camera tracking and the inertial motion capture suit, it is possible to retrieve the position of the joints that are hidden from the camera view. Using the proposed hybrid technique, it is possible to capture the position even if it cannot be captured by the suit sensors. Our system can be used for both realtime tracking and off-line post-processing of already captured mocap data.

  1. submitted: 2018-06-13,
  2. accepted: 2018-09-05,
  3. published: 2019-08-05

Keywords

Fulltext

License

Any party may pass on this Work by electronic means and make it available for download under the terms and conditions of the Digital Peer Publishing License. The text of the license may be accessed and retrieved at http://www.dipp.nrw.de/lizenzen/dppl/dppl/DPPL_v2_en_06-2004.html.

Number of citations

Visit Google Scholar to find out, how often this paper is cited.