Embedded Files
Dataset Information
Dataset Information
The dataset includes recordings from 23 healthy adult participants.
Video Data: Captured using a multi-view camera system during nine activities. Each participant completed at least one minute of overground walking at a self-selected speed, followed by eight lower-extremity functional exercises. Each exercise was performed for a minimum of three successful repetitions.
Code for processing the videos: https://github.com/CMU-MBL/tbme-multiview-markerless-tracking
IMU Data: In addition to the nine activities described above, wearable inertial measurement units (IMUs) captured two minutes of treadmill walking and two minutes of treadmill running for each participant (Data will be released soon).
Ground Truth Data: Motion capture data was processed in OpenSim to generate inverse kinematics (IK) .mot files, and participant-specific scaled musculoskeletal models.
License / Usage Restrictions
License / Usage Restrictions
The CMU I-MOVE-23 dataset is released under the Creative Commons Attribution-NonCommerical-ShareAlike 4.0 international License (CC BY-NC-SA 4.0).
This license allows users to share (copy and redistribute) and adapt (remix, transform, and build upon) the dataset for non-commercial research and educational purposes, under the following conditions:
Attribution (BY): You must give appropriate credit to the dataset, provide a link to this license, and indicate if changes were made.
NonCommercial (NC): You may not use the material for commercial purposes.
ShareAlike (SA): If you remix, transform, or build upon the dataset, you must distribute your contributions under the same license as the original
Full license text: https://creativecommons.org/licenses/by-nc-sa/4.0/
Terms of Use and Reference
Terms of Use and Reference
Intended Use:
The dataset is provided exclusively for academic research, teaching, and non-commercial purposes. Any commercial use, redistribution, or integration into proprietary systems requires prior written permission from the dataset owners.Redistribution:
Redistribution of the dataset, in whole or in part, is not permitted unless it is under the same CC BY-NC-SA 4.0 license and with proper citation and attribution.Citation Requirement:
By using this dataset, users must agree to cite both papers:
Li, Z., Shin, S., Phan, V., Meinders, E., & Halilaj, E. (2025). Impact of multi-view fusion and biomechanical modeling on markerless motion tracking. IEEE Transactions on Biomedical Engineering. https://doi.org/10.1109/TBME.2025.3622032
Phan, V., Li, Z., Meinders, E., Gale, T., Anderst, W., Ng-Thow-Hing, J., Khandan, A., & Halilaj, E. (2025). Inertial motion tracking now matches marker-based tracking accuracy: Rethinking modeling approaches toward future progress. Manuscript in preparation.
No Warranty:
The dataset is provided “as is”, without warranty of any kind. The authors and Carnegie Mellon University are not responsible for any damages or misuse arising from its use.
Acknowledgement
Acknowledgement
This study was funded by the U.S. National Science Foundation under Award CBET 2145473.
Questions?
Questions?
Contact Zhixiong (Jack) Li (videos) , Vu Phan (IMUs) and Dr. Eni Halilaj to get more information on the project.
Page updated
Report abuse