3D pose estimation for scalable remote gait kinematics assessment
Shreyasvi Natraj, Témi Messmer, Yoshiori Fujii, Kenji Suzuki, Robert Riener, Inge Eriks-Hoogland, Diego Paez-Granados · 2025
Read 3D pose estimation for scalable remote gait kinematics assessment by Shreyasvi Natraj, Témi Messmer, Yoshiori Fujii, Kenji Suzuki, Robert Riener, Inge Eriks-Hoogland, Diego Paez-Granados (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12800279.txt.
Description
Shreyasvi Natraj and co-authors built a markerless walking analysis in 2025 that grades gait from a single ordinary video. Laboratory gait labs read movement with reflective markers, at high cost and only in clinic. Continuous, real-world checks matter most in conditions like spinal cord injury, where recovery unfolds at home.
The team first benchmarked leading three-dimensional pose estimation models on injured gait, and one, named in the study, performed best. Its pipeline turns one video into joint angle time series automatically. On the largest spinal cord injury gait set gathered to date, 225 participants, it separated distinct walking patterns on its own and flagged markers like reduced hip and knee motion. Readers get rehabilitation measurement that leaves the lab: a phone camera standing in for a motion capture room.
Catalog record
| CREATOR | Shreyasvi Natraj, Témi Messmer, Yoshiori Fujii, Kenji Suzuki, Robert Riener, Inge Eriks-Hoogland, Diego Paez-Granados |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 81 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |