Improved 3D reconstruction in smart-room environments using ToF imaging

  • Authors:
  • Sigurjón Árni Guímundsson;Montse Pardís;Josep R. Casas;Jóhannes R. Sveinsson;Henrik Aanæs;Rasmus Larsen

  • Affiliations:
  • Technical University of Denmark (DTU), Informatics and Mathematical Modelling, Richard Petersens Plads, Building 321, 2800 Kgs. Lyngby, Denmark and University of Iceland, Department of Electrical ...;Technical University of Catalonia (UPC), Department of Signal Theory and Communications, Jordi Girona 1-3, Edifici D5, 08034 Barcelona, Spain;Technical University of Catalonia (UPC), Department of Signal Theory and Communications, Jordi Girona 1-3, Edifici D5, 08034 Barcelona, Spain;University of Iceland, Department of Electrical and Computer Engineering, Hjaríarhaga 2-6, 107 Reykjavik, Iceland;Technical University of Denmark (DTU), Informatics and Mathematical Modelling, Richard Petersens Plads, Building 321, 2800 Kgs. Lyngby, Denmark;Technical University of Denmark (DTU), Informatics and Mathematical Modelling, Richard Petersens Plads, Building 321, 2800 Kgs. Lyngby, Denmark

  • Venue:
  • Computer Vision and Image Understanding
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper presents the use of Time-of-Flight (ToF) cameras in smart-rooms and how this leads to improved results in segmenting the people in the room from the background and consequently better 3D reconstruction of foreground objects. A calibrated rig consisting of one Swissranger SR3100 Time-of-Flight range camera and a high resolution standard CCD camera is set in a smart-room containing five other standard cameras. A probabilistic background model is used to segment each view and a shape from silhouette volume is reconstructed. It is shown that the presence of the range camera gives ways of eliminating regional artifacts and therefore creating a more robust input for higher level applications such as people tracking or human motion analysis.