login

Color-based tracking of heads and other mobile objects at video frame rates

Published 22 November 2002
Paul Fieguth, Demetri Terzopoulos
Citations239

TL;DR

A simple and very fast method for object tracking based exclusively on color information in digitized video images that demonstrates the efficacy of the technique in the challenging task of tracking people, especially tracking human heads and hands.

Abstract

We develop a simple and very fast method for object tracking based exclusively on color information in digitized video images. Running on a Silicon Graphics R4600 Indy system with an IndyCam, our algorithm is capable of simultaneously tracking objects at full frame size (640/spl times/480 pixels) and video frame rate (30 fps). Robustness with respect to occlusion is achieved via can explicit hypothesis-tree model of the occlusion process. We demonstrate the efficacy of our technique in the challenging task of tracking people, especially tracking human heads and hands.

Keywords

Computer Science