Reality Modeling and Visualization from Multiple Video Sequences

  • Authors:
  • Saied Moezzi;Arun Katkere;Don Y. Kuramura;Ramesh Jain

  • Affiliations:
  • -;-;-;-

  • Venue:
  • IEEE Computer Graphics and Applications
  • Year:
  • 1996

Quantified Score

Hi-index 0.00

Visualization

Abstract

Modeling and life-like interactive visualization of actual events is a challenging but useful capability. In contrast to most current systems, which provide 3D visualization of static environments or premodeled objects, real-event modeling and visualization capability allows us to render, for example, a basketball game or a dance performance in its entirety from any interactively selected viewpoint. While highly detailed 3D modeling of static objects can be achieved using laser scanners, recreating events containing human performers in motion requires sophisticated computer vision and computer graphics techniques. In this article we describe a reality modeling and visualization system that uses multiple videos of an event, captured from different perspectives, to generate a full 3D digital sequence of the moving objects in that event. We formalize our concept of Immersive Video, describe the architecture of our current implementation, and illustrate Immersive Video in staged karate demonstrations.