Improving meeting capture by applying television production principles with audio and motion detection

  • Authors:
  • Abhishek Ranjan;Jeremy Birnholtz;Ravin Balakrishnan

  • Affiliations:
  • University of Toronto, Toronto, Canada;University of Toronto, Toronto, Canada and Cornell University, Ithaca, NY, USA;University of Toronto, Toronto, Canada

  • Venue:
  • Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
  • Year:
  • 2008

Quantified Score

Hi-index 0.01

Visualization

Abstract

Video recordings of meetings are often monotonous and tedious to watch. In this paper, we report on the design, implementation and evaluation of an automated meeting capture system that applies television production principles to capture and present videos of small group meetings in a compelling manner. The system uses inputs from a motion capture system and microphones to drive multiple pan-tilt-zoom cameras and uses heuristics to frame shots and cut between them. An evaluation of the system indicates that its performance approaches that of a professional crew while requiring significantly fewer human resources.