PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Real-time Pointing Gesture Recognition for an Immersive Environment
Roland Kehl and Luc Van Gool
In: Sixth IEEE International Conference on Automatic Face and Gesture Recognition, Seoul, South Korea(2004).

Abstract

We present an algorithm for the real-time detection and interpretation of pointing gestures, performed with one or both arms. The pointing gestures are used as an intuitive tracking interface for a user interacting with an immersive virtual environment. We have defined the pointing direction to correspond to the line of sight connecting the eyes and the pointing fingertip. If a pointing gesture is being performed, the algorithm detects and tracks the position of the user's eyes and fingertip and computes the origin and direction of that gesture with respect to a real-world coordinate system. The algorithm is based on the body silhouettes extracted from multiple views and uses point correspondences to reconstruct in 3D the points of interest. The system doesn't require initial poses, special clothing, or markers.

EPrint Type:Conference or Workshop Item (Poster)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
User Modelling for Computer Human Interaction
ID Code:1751
Deposited By:Roland Kehl
Deposited On:28 November 2005