Dataset of "Towards Artefact Aware Human Motion Capture using Inertial Sensors Integrated into Loose Clothing"

This dataset was used in the publication:
Towards Artefact Aware Human Motion Capture using Inertial Sensors Integrated into Loose Clothing
presented at the IEEE International Conference on Robotics and Automation 2022

Abstract:
Inertial motion capture has become an attractive alternative to optical motion capture for human joint angle estimation outside the laboratory. Usually inertial sensors are assumed to be tightly fixed to the body segments, which can be cumbersome regarding setup-time and ease-of-use. However, integrating the sensors directly into clothing, usually, results in additional clothing motion relative to the motion of the underlying bones that should be captured.
In this work we propose the Difference Mapping distributions approach that corrects the segment orientations of a given inertial motion capture system that assumes tightly coupled sensors.
The approach allows to reduce the joint angle errors due to clothing artefacts by at least 77.2 percent for people with similar morphology performing a similar task as seen in the training data, including an ergonomic assessments scenario at work places with 10 participants.  
Moreover, we show that the uncertainty of the distribution can be used to measure the reliability of the predicted map if e.g. the motion is further away from the training data to allow for an artefact aware inertial motion tracking approach.
The experimental data for this study is available online

Data structure:
The data contains trials of 12 subjects for different motions, wearing at the same time a tight setup with inertial sensors and a loose working suit with integrated inertial sensors. It contains the raw IMU data, raw Magnetometer data and the estimated segment orientations using a Sensor Fusion engine provided by Sci-Track.
Please note, that in the publication only the first 10 subjects were used and the upper body information was used only. The Sternum sensor of the tight setup of subjects 11, 12 and 13  tilted slowly during the long-term measurements. For this reason only 10 subjects were included in the study. However all remaining sensor of the tight setup were not tilted during recording. In particular the lower body recordings of all subjects are not corrupted.

Code samples, a visualizer and further useful information is provided under the following git repository:
https://github.com/lorenzcsunikl/Dataset-of-Artefact-Aware-Human-Motion-Capture-using-Inertial-Sensors-Integrated-into-Loose-Clothing