Improving Full-Body Pose Estimation from a Small Sensor Set Using Artificial Neural Networks and a Kalman Filter

  • Frank J. Wouda University of Twente
  • Matteo Giuberti Xsens Technologies B. V.
  • Giovanni Bellusci Xsens Technologies B. V.
  • Bert-Jan F. van Beijnum University of Twente
  • Peter H. Veltink University of Twente


Previous research has shown that estimating full-body poses from a minimal sensor set using a trained ANN without explicitly enforcing time coherence has resulted in output pose sequences that occasionally show undesired jitter. To mitigate such effect, we propose to improve the ANN output by combining it with a state prediction using a Kalman Filter. Preliminary results are promising, as the jitter effects are diminished. However, the overall error does not decrease substantially.

Student Abstract Track