Bayesian Estimation of 3-D Human Motion

    •  Michael E. Leventon, William T. Freeman, "Bayesian Estimation of 3-D Human Motion", Tech. Rep. TR98-06, Mitsubishi Electric Research Laboratories, Cambridge, MA, July 1998.
      BibTeX Download PDF
      • @techreport{MERL_TR98-06,
      • author = {Michael E. Leventon and William T. Freeman},
      • title = {Bayesian Estimation of 3-D Human Motion},
      • institution = {MERL - Mitsubishi Electric Research Laboratories},
      • address = {Cambridge, MA 02139},
      • number = {TR98-06},
      • month = jul,
      • year = 1998,
      • url = {}
      • }
  • Research Areas:

    Computer Vision, Machine Learning

We address the problem of reconstructing the 3-dimensional motions of a human figure from a monocular image sequence. We take a statistical approach, and use a set of motion capture examples to build a gaussian probability model for short human motion sequences. We first study this model in a simplified rendering domain. This yields analytic results for the optimal 3-d estimate given a 2-d temporal sequence, as well as for which motion modes are difficult to estimate. The results from the simplified rendering conditions show that if we can overlay a stick figure on an image of a moving human, we can estimate his or her 3-d motion well. We built an interactive tracking system to process real video sequences, and can achieve good 3-d reconstructions of the human figure motion.