Data-driven motion estimation with low-cost sensors Conference Paper uri icon

abstract

  • Motion capture can produce high quality data for motion generation. However, professional motion capture is expensive, and imposes restrictions on the capturing environment. We propose a motion estimation framework that utilizes a small set of low-cost, 3D acceleration sensors. We use a data-driven approach to synthesize realistic human motion comparable in quality to the motion generated by the professional motion capture systems. We employ eight 3D accelerometers - four Nintendo Wii controllers - attached to a performer's body as the input signal, which is used to synthesize high quality motion from a statistical model learned from a high quality motion capture database. The proposed system is inexpensive and is easy to setup. 2008 The Institution of Engineering and Technology.

name of conference

  • 5th International Conference on Visual Information Engineering (VIE 2008)

published proceedings

  • 5th International Conference on Visual Information Engineering (VIE 2008)

author list (cited authors)

  • Liguang Xie, .., Kumar, M., Yong Cao, .., Gracanin, D., & Quek, F.

citation count

  • 5

complete list of authors

  • Kumar, M||Gracanin, D||Quek, F

publication date

  • January 2008