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

Authors

  • 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

DOI:

https://doi.org/10.1609/aaai.v33i01.330110063

Abstract

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.

AAAI-19 Proceedings Cover

Downloads

Published

2019-07-17

How to Cite

Wouda, F. J., Giuberti, M., Bellusci, G., van Beijnum, B.-J. F., & Veltink, P. H. (2019). Improving Full-Body Pose Estimation from a Small Sensor Set Using Artificial Neural Networks and a Kalman Filter. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 10063-10064. https://doi.org/10.1609/aaai.v33i01.330110063

Issue

Vol. 33 No. 01: AAAI-19, IAAI-19, EAAI-20

Section

Student Abstract Track