An Adaptive IMU–Visual Multimodal Fusion System for Real-Time Exercise Recognition and Movement Quality Assessment
Zhaoyang Gu, Ruopeng Yang, Yongqi Shi, Dongxu Dai, Chaoyang Li, Bo Huang, Kaige Jiao, Yu Tao, Yongqi Wen, Yihao Zhong, Chen He · 2026
Read An Adaptive IMU–Visual Multimodal Fusion System for Real-Time Exercise Recognition and Movement Quality Assessment by Zhaoyang Gu, Ruopeng Yang, Yongqi Shi, Dongxu Dai, Chaoyang Li, Bo Huang, Kaige Jiao, Yu Tao, Yongqi Wen, Yihao Zhong, Chen He (2026) 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-13611031.txt.
Description
A coaching system that watches workouts with both a camera and a wrist sensor is presented in a 2026 study by Zhaoyang Gu and co-authors. Vision alone loses joints when limbs hide behind the body; inertial sensors never lose the limb but cannot see whole posture.
The prototype runs two streams, one learning from motion-sensor dynamics and one from pose keypoints over time, and a confidence gate leans on whichever stream is trustworthy at the moment. Finding no public data set with synchronized views, the team built one: ten people, three exercises, nine hundred repetitions filmed from side, front, and back. Under leave-one-person-out testing, recognition hit ninety-six percent. The system also grades movement quality for supervised training.
Catalog record
| CREATOR | Zhaoyang Gu, Ruopeng Yang, Yongqi Shi, Dongxu Dai, Chaoyang Li, Bo Huang, Kaige Jiao, Yu Tao, Yongqi Wen, Yihao Zhong, Chen He |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 59 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |