Assessment of the Accuracy of a Deep Learning Algorithm- and Video-based Motion Capture System in Estimating Snatch Kinematics
FEDERICO THIELE, FLORIAN PATERNOSTER, CHRIS HUMMEL, FABIAN STÖCKER, DENIS HOLZER · 2024
Read Assessment of the Accuracy of a Deep Learning Algorithm- and Video-based Motion Capture System in Estimating Snatch Kinematics by FEDERICO THIELE, FLORIAN PATERNOSTER, CHRIS HUMMEL, FABIAN STÖCKER, DENIS HOLZER (2024) 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-11728585.txt.
Description
Federico Thiele and four co-authors test a markerless video system for measuring the snatch lift in weightlifting in this 2024 paper. Marker-based motion capture is the reference but impractical in training or contests. The video system uses deep learning pose estimation instead.
Twenty-one lifters performed snatches at three loads while both systems recorded, giving one hundred thirty-one trials. Joint positions differed by about five centimeters on average between systems. Joint angles agreed best in the frontal plane, less in the side plane. Peak extension angles and speeds in the second pull also differed significantly. The authors blame differing body models rather than raw accuracy. They still see promise as the networks improve.
Catalog record
| CREATOR | FEDERICO THIELE, FLORIAN PATERNOSTER, CHRIS HUMMEL, FABIAN STÖCKER, DENIS HOLZER |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 33 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |