Motion capture data recovery using skeleton constrained singular value thresholding

Cheen-Hau Tan, Junhui Hou, Lap-Pui Chau

Abstract: Motion capture data could be missing due to imperfections during the acquisition process. Singular value thresholding (SVT) is an effective method to recover missing motion capture data. However, its effectiveness decreases significantly when markers are missing for longer periods of time. To alleviate this problem, we utilize the fact that human bones are rigid to constrain inter-marker distances of specific sets of markers. We extend the SVT method for mocap recovery to include skeleton constraints. On average, our proposed method improves on the SVT method by 40 %, and performs 4 % better than a recent state-of-the-art method at up to 11 times faster computation time.