Hybrid Model-Based Motion Capture System

This proposal describes a Hybrid Model-Based Motion Capture System which uses a unique, low-cost, credit-card-sized range-image detector and conventional sensors to augment an image-understanding system suitable for tracking cooperative users. The resulting system will combine the best features of aided and unaided optical tracking systems into a single new product with broad application in military and commercial markets. Room setup will be minimized through the use of the modular range-image detector. Robust tracking of key body parts will be achieved through the use of minimally invasive optical targets and gyros integrated into standard I/O devices like microphone/headsets and 3D mice. The remaining body states will be estimated using visual understanding algorithms working from the range-image data generated by the range image detector. A 22 DOF human model will be at the heart of an inverse kinematic estimation filter, combining together all sources of information to track, predict, understand, and render the state of the human operator. A demonstration and sensor evaluation test bed will be developed. Such a tracking subsystem could become a workhorse for the military and commercial motion capture markets.