Event-Domain Knowledge in Inertial Sensor Based State Estimation of Human Motion

EasyChair Preprint 7641

Abstract

State estimation can significantly benefit from prior knowledge about a system’s dynamics and state. In this paper, we investigate a special class of prior knowledge: Events that correspond to a subset of the state space. This class of knowledge was introduced in pedestrian activity classification to improve the position estimation. We argue that the methodology can be generalized and applied to other applications in human motion tracking, in which the same class of knowledge is available. We apply this methodology to estimate the pose of climbers using inertial sensors and previously measured route maps. For our evaluation, we collected an open source dataset with 27 participants, including IMU data and ground truth positions of the hands. We detect gripping holds (as events), estimate the transition between holds in a least squares optimizer and use a particle filter to deploy the route map constraints (as state subset). In this scenario, our approach achieves a position median of 0.133m and thus demonstrates its possible effectiveness for this application class.

Keyphrases: IMU, INS, PDR, ZUPT, bouldering, event-domain knowledge, human motion tracking, prior knowledge

@booklet{EasyChair:7641,
  author    = {Tom Lucas Koller and Tim Laue and Udo Frese},
  title     = {Event-Domain Knowledge in Inertial Sensor Based State Estimation of Human Motion},
  howpublished = {EasyChair Preprint 7641},
  year      = {EasyChair, 2022}}