Pfinder: Real-Time Tracking of the Human Body

by

Christopher R. Wren

Submitted to the Department of Electrical Engineering and Computer Science

in partial fulfillment of the requirements for the degree of

Masters of Science in Electrical Engineering and Computer Science

at the

MASSACHUSETTS INSTITUTE OF TECHNOLOGY

September 1996

©Massachusetts Institute of Technology 1996. All rights reserved.

Author
		August 1, 1996
		Department of Electrical Engineering and Computer Science
Certified by
		Alex P. Pentland
		Associate Professor
		Thesis Supervisor
Accepted by
		Frederic R. Morgenthaler
		Chairman, Department Committee on Graduate Students

 
• Contents
• List of Figures
• List of Tables
• Introduction
  • Related Work
  • Motivation
• Steady State Tracking
  • Modeling The Person
  • Modeling The Scene
  • The Analysis Loop
    • Predict Model Parameters
    • Measure Likelihoods For Each Class
      • Shadowing.
    • Determine Support Map
      • Morphology.
    • Update Models
      • Blending Measurements and Priors.
• Initialization and Recovery
  • Learning The Scene
  • Detect Person
  • Building the Person Model
    • Occlusion.
    • Contour Analysis
    • Integrating of Blob and Contour Features
• Performance
  • Classification Performance
  • Runtime Performance
• Applications
  • SURVIVE
  • Visually-Animated Characters
  • NetSpace
  • American Sign Language
  • DanceSpace
  • ALIVE
• Future Work
• Multi-Class Classification
• Color Spaces
• References
• About this document ...