Abstract
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.
Highlights
People, even without training, can move in expressive ways to play charades, pantomime a winning touchdown, or act out a story for a child
We build on research in recovering motion from video, in creating animations from motion capture data, and on performance animation systems
A synthetic articulated model of the human form was first rendered online and the synthetic silhouettes were compared with the real ones
Summary
Even without training, can move in expressive ways to play charades, pantomime a winning touchdown, or act out a story for a child. Three dimensional (3D) human motion tracking is most relevant to our work [Yamamoto et al 1998; Bregler and Malik 1998; Delamarre and Faugeras 1999; Sminchisescu and Triggs 2003]. These systems assume accurate initialization, and subsequently track pose changes based on an articulated 3D human model. The tracking approach of Delamarre and Faugeras [1999] is closely related to our own in setup: three synchronized cameras were used to compute silhouettes In their approach, a synthetic articulated model of the human form was first rendered online and the synthetic silhouettes were compared with the real ones. Few papers describe systems that can track complex motions or motion with significant yaw rotation for more than a few seconds
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
