Practical color-based motion capture

Abstract

Motion capture systems track the 3-D pose of the human body and are widely used for high quality content creation, gestural user input and virtual reality. However, these systems are rarely deployed in consumer applications due to their price and complexity. In this thesis, we propose a motion capture system built from commodity components that can be deployed in a matter of minutes. Our approach uses one or more webcams and a color garment to track either the user's upper body or hands for motion capture and user input. We demonstrate that custom designed color garments can simplify difficult computer vision problems and lead to efficient and robust algorithms for hand and upper body tracking. Specifically, our highly descriptive color patterns alleviate ambiguities that are commonly encountered when tracking only silhouettes or edges, allowing us to employ a nearest-neighbor approach to track either the hands or the upper body at interactive rates. We also describe a robust color calibration system that enables our color-based tracking to work against cluttered backgrounds and under multiple illuminants. We demonstrate our system in several real-world indoor and outdoor settings and describe proof-of-concept applications enabled by our system that we hope will provide a foundation for new interactions in computer aided design, animation control and augmented reality.