Title: Understanding Expressive Action
|Submitted by:||Christopher R. Wren|
|MIT Media Lab|
|20 Ames St. E15-384|
|Cambridge, MA 02139|
Date of submission: June 15, 1999
Expected Date of Completion: December 19, 1999
|Laboratory where thesis will be done:||MIT Media Lab|
|Vision and Modeling Group|
|Alex P. Pentland, supervisor|
Brief Statement of the Problem:
User interfaces make measurements of the user and use those measurements to give the user control over some abstract domain. The sophistication of these measurements range from the trivial keyclick to the most advanced perceptual interface system. Once the measurements are acquired the system usually attempts to extract some set of features as the first step in a pattern recognition system that will convert those measurements into whatever domain of control the application provides. Those features are usually chosen for mathematical convenience or to satisfy an ad hoc notion of invariance. The expressivity of any such interface is limited by the user's ability to overcome the reality of their bodies and perform in this arbitrary feature space.
The fact that people are embodied places powerful constraints on their motion. An appropriate model of this embodiment allows a perceptual system to separate the necessary aspects of motion from the purposeful aspects of motion. The necessary aspects are a result of physics, and are predictable. The purposeful aspects are the direct result of a person attempting to express themselves through the motion of their bodies. By taking this one thoughtful step closer to the original intentions of the user, we open the door to better interfaces. Understanding embodiment is the key to perceiving expressive motion.