Sports Ball Detection And Tracking On 1
Métriques
Accuracy (%)
Average Precision (%)
F1 (%)
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | Accuracy (%) | Average Precision (%) | F1 (%) | Paper Title | Repository |
|---|---|---|---|---|---|
| BallSeg | 17.5 | 8.5 | 19.5 | Real-time CNN-based Segmentation Architecture for Ball Detection in a Single View Setup | |
| DeepBall | 50.7 | 49.2 | 64.4 | DeepBall: Deep Neural-Network Ball Detector | |
| WASB (Step=1) | 80.0 | 83.2 | 88.0 | Widely Applicable Strong Baseline for Sports Ball Detection and Tracking | |
| WASB (Step=3) | 77.9 | 79.9 | 86.5 | Widely Applicable Strong Baseline for Sports Ball Detection and Tracking | |
| MonoTrack | 75.9 | 72.1 | 85.1 | MonoTrack: Shuttle trajectory reconstruction from monocular badminton video | |
| DeepBall-Large | 57.5 | 56.5 | 70.4 | Widely Applicable Strong Baseline for Sports Ball Detection and Tracking | |
| TrackNetV2 | 73.8 | 72.3 | 83.6 | TrackNetV2: Efficient Shuttlecock Tracking Network | |
| ResTrackNetV2 | 74.7 | 74.7 | 84.2 | Widely Applicable Strong Baseline for Sports Ball Detection and Tracking |
0 of 8 row(s) selected.