Research on intelligent generation of volleyball training strategies combining YOLOv5 + DeepSORT trajectory data and a key point CNN model
Liang Zhao · 2026
Read Research on intelligent generation of volleyball training strategies combining YOLOv5 + DeepSORT trajectory data and a key point CNN model by Liang Zhao (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/PMC13550479.txt.
Description
Liang Zhao tests a video intelligence system that watches volleyball practice and turns what it sees into tailored drills, in a 2026 study. The pipeline detects players with a standard object detector and tracks their trajectories with a sorting algorithm. A neural network then reads body keypoints. From those it judges jump mechanics, approach angles, and arm-swing and block timing. Fifty-six competitive athletes trained for six weeks, half with the system's real-time feedback and half with standard coaching.
The supported group improved more across transition speed, serve-receive accuracy, rotation speed, defensive coverage, jump height, and timing consistency. Match-like indicators such as side-out rate and attack efficiency also rose further, and several gains survived one to two weeks later. Zhao concludes that fused trajectory and keypoint data can sharpen coaching decisions, pending tests in other venues and competitions.
Catalog record
| CREATOR | Liang Zhao |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 89861 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |