Fast Multiple Camera Head Pose Tracking

Abstract

This paper presents a multiple camera system to determine the head pose of people in an indoor setting. Our approach extends current eye tracking techniques from a single camera system to a multiple camera system. The head pose of a person is determined by triangulating multiple facial features that are obtained in real-time from eye trackers. Our work is unique in that it allows us to observe user head orientation in real-time using several cameras over a much larger space than covered by a single camera. We demonstrate the viability of this system by experimenting with several people under di#erent lighting conditions performing head movements.