JointTracker: Real-time inertial kinematic chain tracking with joint position estimation [version 2; peer review: 1 approved, 2 approved with reservations]
In-field motion capture is drawing increasing attention due to the multitude of application areas, in particular for human motion capture (HMC). Plenty of research is currently invested in camera-based markerless HMC, however, with the inherent drawbacks of limited field of view and occlusions. In c...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
F1000 Research Ltd
2025-01-01
|
| Series: | Open Research Europe |
| Subjects: | |
| Online Access: | https://open-research-europe.ec.europa.eu/articles/4-33/v2 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832591174799458304 |
|---|---|
| author | Michael Lorenz Didier Stricker Markus Miezal Gabriele Bleser-Taetz Bertram Taetz |
| author_facet | Michael Lorenz Didier Stricker Markus Miezal Gabriele Bleser-Taetz Bertram Taetz |
| author_sort | Michael Lorenz |
| collection | DOAJ |
| description | In-field motion capture is drawing increasing attention due to the multitude of application areas, in particular for human motion capture (HMC). Plenty of research is currently invested in camera-based markerless HMC, however, with the inherent drawbacks of limited field of view and occlusions. In contrast, inertial motion capture does not suffer from occlusions, thus being a promising approach for capturing motion outside the laboratory. However, one major challenge of such methods is the necessity of spatial registration. Typically, during a predefined calibration sequence, the orientation and location of each inertial sensor are registered with respect to an underlying skeleton model. This work contributes to calibration-free inertial motion capture, as it proposes a recursive estimator for the simultaneous online estimation of all sensor poses and joint positions of a kinematic chain model like the human skeleton. The full derivation from an optimization objective is provided. The approach can directly be applied to a synchronized data stream from a body-mounted inertial sensor network. Successful evaluations are demonstrated on noisy simulated data from a three-link chain, real lower-body walking data from 25 young, healthy persons, and walking data captured from a humanoid robot. |
| format | Article |
| id | doaj-art-8a83ee11e8c740d79d34327e4296ffc1 |
| institution | Kabale University |
| issn | 2732-5121 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | F1000 Research Ltd |
| record_format | Article |
| series | Open Research Europe |
| spelling | doaj-art-8a83ee11e8c740d79d34327e4296ffc12025-01-23T01:00:00ZengF1000 Research LtdOpen Research Europe2732-51212025-01-01420759JointTracker: Real-time inertial kinematic chain tracking with joint position estimation [version 2; peer review: 1 approved, 2 approved with reservations]Michael Lorenz0https://orcid.org/0009-0000-4535-330XDidier Stricker1Markus Miezal2Gabriele Bleser-Taetz3https://orcid.org/0000-0002-7283-8166Bertram Taetz4Augmented Vision, German Research Center for Artificial Intelligence, Kaiserslautern, Rhineland-Palatinate, 67663, GermanyAugmented Vision, German Research Center for Artificial Intelligence, Kaiserslautern, Rhineland-Palatinate, 67663, GermanyAugmented Vision, German Research Center for Artificial Intelligence, Kaiserslautern, Rhineland-Palatinate, 67663, GermanyAugmented Vision, German Research Center for Artificial Intelligence, Kaiserslautern, Rhineland-Palatinate, 67663, GermanyAugmented Vision, German Research Center for Artificial Intelligence, Kaiserslautern, Rhineland-Palatinate, 67663, GermanyIn-field motion capture is drawing increasing attention due to the multitude of application areas, in particular for human motion capture (HMC). Plenty of research is currently invested in camera-based markerless HMC, however, with the inherent drawbacks of limited field of view and occlusions. In contrast, inertial motion capture does not suffer from occlusions, thus being a promising approach for capturing motion outside the laboratory. However, one major challenge of such methods is the necessity of spatial registration. Typically, during a predefined calibration sequence, the orientation and location of each inertial sensor are registered with respect to an underlying skeleton model. This work contributes to calibration-free inertial motion capture, as it proposes a recursive estimator for the simultaneous online estimation of all sensor poses and joint positions of a kinematic chain model like the human skeleton. The full derivation from an optimization objective is provided. The approach can directly be applied to a synchronized data stream from a body-mounted inertial sensor network. Successful evaluations are demonstrated on noisy simulated data from a three-link chain, real lower-body walking data from 25 young, healthy persons, and walking data captured from a humanoid robot.https://open-research-europe.ec.europa.eu/articles/4-33/v2inertial motion capture 3D kinematics 3D human pose estimation online joint position estimation calibration-free recursive state estimationeng |
| spellingShingle | Michael Lorenz Didier Stricker Markus Miezal Gabriele Bleser-Taetz Bertram Taetz JointTracker: Real-time inertial kinematic chain tracking with joint position estimation [version 2; peer review: 1 approved, 2 approved with reservations] Open Research Europe inertial motion capture 3D kinematics 3D human pose estimation online joint position estimation calibration-free recursive state estimation eng |
| title | JointTracker: Real-time inertial kinematic chain tracking with joint position estimation [version 2; peer review: 1 approved, 2 approved with reservations] |
| title_full | JointTracker: Real-time inertial kinematic chain tracking with joint position estimation [version 2; peer review: 1 approved, 2 approved with reservations] |
| title_fullStr | JointTracker: Real-time inertial kinematic chain tracking with joint position estimation [version 2; peer review: 1 approved, 2 approved with reservations] |
| title_full_unstemmed | JointTracker: Real-time inertial kinematic chain tracking with joint position estimation [version 2; peer review: 1 approved, 2 approved with reservations] |
| title_short | JointTracker: Real-time inertial kinematic chain tracking with joint position estimation [version 2; peer review: 1 approved, 2 approved with reservations] |
| title_sort | jointtracker real time inertial kinematic chain tracking with joint position estimation version 2 peer review 1 approved 2 approved with reservations |
| topic | inertial motion capture 3D kinematics 3D human pose estimation online joint position estimation calibration-free recursive state estimation eng |
| url | https://open-research-europe.ec.europa.eu/articles/4-33/v2 |
| work_keys_str_mv | AT michaellorenz jointtrackerrealtimeinertialkinematicchaintrackingwithjointpositionestimationversion2peerreview1approved2approvedwithreservations AT didierstricker jointtrackerrealtimeinertialkinematicchaintrackingwithjointpositionestimationversion2peerreview1approved2approvedwithreservations AT markusmiezal jointtrackerrealtimeinertialkinematicchaintrackingwithjointpositionestimationversion2peerreview1approved2approvedwithreservations AT gabrieleblesertaetz jointtrackerrealtimeinertialkinematicchaintrackingwithjointpositionestimationversion2peerreview1approved2approvedwithreservations AT bertramtaetz jointtrackerrealtimeinertialkinematicchaintrackingwithjointpositionestimationversion2peerreview1approved2approvedwithreservations |