cjenkins: Research Projects

Motion capture without cumbersome infrastructure using inertial sensing.
Appliation to humanoid robot teleoperation (large movies): Robonaut Test 1 (qt),Robonaut Test 2 (qt),Segwanaut Demo (avi).
My dissertation research focused on the problem of automatically deriving behavior modules from human motion data for controlling humanoid robots and classifying human motion.
Markerless motion capture without an a priori kinematic model.
Motion classification using vector quantization and human demonstrated primitive motions.
Optical character recogntion for musical composition and typesetting. (gtaubman's thesis)