Abstract:

It might seem that an interface based on computer vision would require visual competence near the level of a human being, which is still beyond the state of the art. Fortunately, the interactive application often constrains the vision problem to be solved, allowing fast and simple vision algorithms to be used. This paper gives a brief survey of existing vision-based interactive systems. These systems typically use a number of basic vision algorithms. We describe the basic algorithms used by some systems we have built at MERL: vision-based computer games, a television set controlled by hand gestures, and 3-D head tracking.