Con guration States for the Representation and Recognition of Gesture

A state-based technique for the representation and recognition of gesture is presented. We de ne a gesture to be a sequence of states in a measurement or con guration space. For a given gesture, these states are used to capture both the reapeatability and variability evidenced in a training set of example trajectories. Using techniques for computing a prototype trajectory of an ensemble of trajectories, we develop methods for de ning con guration states along the prototype, and for recognizing gestures from an unsegmented, continuous stream of sensor data. The approach is illustrated by application to a range of gesture-related sensory data: the two-dimensional movements of a mouse input device, the movement of the hand measured by a magnetic spatial position and orientation sensor, and, lastly, the changing eigenvector projection coe cients computed from an image sequence.