NEW CLOSED FORM SOLUTIONS FOR SKELETAL EXTRACTION FROM MOTION CAPTURE

We present a fast closed form solution for estimating the exact joint locations inside the human body from motion capture data. The new closed-form solution is more robust and faster. For example, the formulae are as much as about 100 times faster than the traditional non-linear Maximum Likelihood Estimator and about 9 times faster than linear least squares methods. The methods are proven to be statistically efficient when measurement error is smaller than the joint-marker distance. Unbiased Generalized Delogne-Kdsa (UGDK), multiple radii solution, and incremental GDK are important contributions of our research providing closed form fast solutions for skeleton extraction from motion capture data. Skeletal animation sequences are generated using the CMU and Eric Camper's motion capture database.