We have developed a novel vision system that can recognize people by the way they walk. The system computes optical flow for an image sequence of a person walking, and then characterizes the shape of the motion with a set of sinusoidally-varying scalars. Feature vectors composed of the phases of the sinusoids are able to discriminate among people.

Contents

To Contact the Authors:

• Jim Little is at the University of British Columbia, Department of Computer Science. Send e-mail to:
  little@cs.ubc.ca

• Jeff Boyd is at the Department of Computer Science, University of Calgary. Send e-mail to:
  boyd@cpsc.ucalgary.ca