Joshua Weaver

We present two real-time hidden Markov model-based systems for recognizing sentence-level continuous American sign language (ASL) using a single camera to track the user's unadorned hands. The first system observes the user from a desk mounted camera and achieves 92 percent word accuracy. The second system mounts the camera in a cap worn by the user and achieves 98 percent accuracy (97 percent with an unrestricted grammar). Both experiments use a 40-word lexicon.

This paper describes what we see as fundamental difficulties in both the pure ubiquitous computing and pure wearable computing paradigms when applied to context-aware applications. In particular, ubiquitous computing and smart room systems tend to have difficulties with privacy and personalization, while wearable systems have trouble with localized information, localized resource control, and resource management between multiple people. These difficulties are discussed and a peer-to-peer network of wearable and ubiquitous computing components is proposed as a solution. This solution is demonstrated through several implemented applications.

We propose a practical application of wearable computing and augmented reality which enhances the game of billiards. A vision algorithm is implemented which operates in interactive-time with the user to assist planning and aiming. Probabilistic color models and symmetry operations are used to localize the table, pockets and balls through a video camera near the user's eye. Classification of the objects of interest is performed and each possible shot is ranked in order to determine its relative usefulness. The system allows the user to proceed through a regular pool game while it automatically determines strategic shots. The resulting trajectories are rendered as graphical overlays on a head mounted live video display. The wearable video output and the computer vision system provide an integration of real and virtual environments which enhances the experience of playing and learning the game of billiards without encumbering the player.