TR99-37

Bayesian Reconstruction of 3D Human Motion from Single-Camera Video


    •  Nicholas R. Howe, Michael E. Leventon, William T. Freeman, "Bayesian Reconstruction of 3D Human Motion from Single-Camera Video", Tech. Rep. TR99-37, Mitsubishi Electric Research Laboratories, Cambridge, MA, October 1999.
      BibTeX TR99-37 PDF
      • @techreport{MERL_TR99-37,
      • author = {Nicholas R. Howe, Michael E. Leventon, William T. Freeman},
      • title = {Bayesian Reconstruction of 3D Human Motion from Single-Camera Video},
      • institution = {MERL - Mitsubishi Electric Research Laboratories},
      • address = {Cambridge, MA 02139},
      • number = {TR99-37},
      • month = oct,
      • year = 1999,
      • url = {https://www.merl.com/publications/TR99-37/}
      • }
  • Research Areas:

    Artificial Intelligence, Computer Vision

Abstract:

Three-dimensional motion capture for human subjects is underde- termined when the input is limited to a single camera, due to the inherent 3D ambiguity of 2D video. We present a system that re- constructs the 3D motion of human subjects from single-camera video, relying on prior knowledge about human motion, learned from training data, to resolve those ambiguities. After initializa- tion in 2D, the tracking and 3D reconstruction is automatic; we show results for several video sequences. The results show the power of treating 3D body tracking as an inference problem.