We present a vision-based performance interface for controlling animated human characters. The system combines information about the user's motion contained in silhouettes from several viewpoints with domain knowledge contained in a motion capture database to interactively produce a high quality animation. Such an interactive system will be useful for authoring, teleconferencing, or as a control interface for a character in a game. In our implementation, the user performs in front of three

more »

... cameras; the resulting silhouettes are used to estimate his orientation and body configuration based on a set of discriminative local features. Those features are selected by a machine learning algorithm during a preprocessing step. Sequences of motions that approximate the user's actions are extracted from the motion database and scaled in time to match the speed of the user's motion. We use swing dancing, an example of complex human motion, to demonstrate the effectiveness of our approach. We compare the results obtained with our approach to those obtained with a set of global features, Hu moments, and to ground truth measurements from a motion capture system.