learning silhouette features for control of human motion.pdf

Learning Silhouette Features for Control of Human Motion LIU REN Carnegie Mellon University GREGORY SHAKHNAROVICH Massachusetts Institute of Technology JESSICA K. HODGINS Carnegie Mellon University HANSPETER PFISTER Mitsubishi Electric Research Laboratories and PAUL VIOLA Microsoft Research We present a vision-based performance interface for controlling animated human characters. The system interactively combines information about the user’s motion contained in silhouettes from three viewpoints with domain knowledge contained in a motion capture database to produce an animation of high quality. Such an interactive system might be useful for authoring, for teleconferencing, or as a control interface for a character in a game. In our implementation, the user performs in front of three video 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, a complex human motion, to demonstrate the effectiveness of our approach. We compare our results to those obtained with a set of global features, Hu moments, and ground truth measurements from a motion capture system. Categories and Subject Descriptors: I.3.7 [Computer Graphics]: Three-Dimensional Graphics and Realism—Animation ; H.5.2 [Information Interfaces and Presentation]: User Interfaces—Input devices and strategies, interaction styles (e.g., commands, menus, forms, direct manipulation); I.2.6 [Artificial Intelligence]: Learning; I.4.8 [Image Processing and Computer Vision]: Scene Analysis—Motion, tracking General Terms: Algorithm Additional Key Words and Phrases: Performance animation, motion control, motion capture, an