Views
No views yet
player and shuttlecock. Used to track the two singles players (and, secondarily,
the shuttle) in a hybrid CV + VLM tactical-analysis pipeline.task=detect)player (0), shuttlecock (1)yolo11s.pt (Ultralytics)Note on the shuttle: this model'sshuttlecockclass is low-recall (small, fast object). For shuttle tracking we use a dedicated higher-resolution model (badminton-shuttlecock-yolov11) atimgsz=1280; this detector is primarily a player detector.
1from ultralytics import YOLO
2from huggingface_hub import hf_hub_download
3
4w = hf_hub_download("<your-username>/badminton-players-yolov11", "game_object_yolo11s.pt")
5model = YOLO(w)
6
7res = model.predict("frame.jpg", imgsz=960, conf=0.25)[0]
8for b in res.boxes:
9 cls = model.names[int(b.cls)] # 'player' | 'shuttlecock'
10 xyxy = b.xyxy[0].tolist()| Base model | yolo11s.pt |
| Epochs | 150 |
| Image size | 960 |
| Batch | 4 |
| Dataset | Roboflow Universe — Badminton Players Detection (hongy20) |
| Dataset link | https://universe.roboflow.com/hongy20/badminton-players-detection-gwgb1 |
| Metric | Value |
|---|---|
| Precision (box) | 0.946 |
| Recall (box) | 0.724 |
| mAP@50 (box) | 0.781 |
| mAP@50-95 (box) | 0.568 |
The combined mAP is pulled down by the hardshuttlecockclass; player detection is the reliable output of this model. Per-class breakdown was not stored in the checkpoint.
1@software{jocher2023yolo,
2 author = {Jocher, Glenn and Qiu, Jing and Chaurasia, Ayush},
3 title = {Ultralytics YOLO},
4 url = {https://github.com/ultralytics/ultralytics},
5 version = {11.0.0}, year = {2024}
6}
7@misc{roboflow_badminton_players,
8 title = {Badminton Players Detection Dataset},
9 author = {hongy20},
10 howpublished = {\url{https://universe.roboflow.com/hongy20/badminton-players-detection-gwgb1}},
11 journal = {Roboflow Universe}, publisher = {Roboflow}, year = {20XX}
12}