9th International Conference on Body Area Networks

Research Article

Ambulatory inertial spinal tracking using constraints

Download41 downloads
  • @INPROCEEDINGS{10.4108/icst.bodynets.2014.256955,
        author={Markus Miezal and Bertram Taetz and Norbert Schmitz and Gabriele Bleser},
        title={Ambulatory inertial spinal tracking using constraints},
        proceedings={9th International Conference on Body Area Networks},
        publisher={ICST},
        proceedings_a={BODYNETS},
        year={2014},
        month={11},
        keywords={inertial motion capture sensor fusion body sensor network},
        doi={10.4108/icst.bodynets.2014.256955}
    }
    
  • Markus Miezal
    Bertram Taetz
    Norbert Schmitz
    Gabriele Bleser
    Year: 2014
    Ambulatory inertial spinal tracking using constraints
    BODYNETS
    ACM
    DOI: 10.4108/icst.bodynets.2014.256955
Markus Miezal1,*, Bertram Taetz1, Norbert Schmitz1, Gabriele Bleser1
  • 1: DFKI GmbH
*Contact email: markus.miezal@dfki.de

Abstract

Wearable inertial sensor networks represent a well-known and meanwhile cheap solution for in-field motion capturing. However, the majority of existing approaches and products rely on simple stick figure models to approximate the human skeleton with only a few rigid segments and connecting joints. Especially the spine is often extremely simplified with one or at most two segments. This simplification results in significant kinematic estimation errors. This paper presents a novel inertial tracking approach, where a recursive filter with integrated constraints enables detailed and efficient estimation of the spine kinematics in real time. The advantages of the proposed approach are confirmed in experiments using ground truth data from an optical reference system.