Sports Ball Detection And Tracking On Tennis
Métriques
Accuracy (%)
Average Precision (%)
F1 (%)
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Accuracy (%) | Average Precision (%) | F1 (%) |
|---|---|---|---|
| deepball-deep-neural-network-ball-detector | 32.3 | 47.0 | 47.4 |
| widely-applicable-strong-baseline-for-sports | 91.8 | 94.2 | 95.6 |
| monotrack-shuttle-trajectory-reconstruction | 85.9 | 87.3 | 92.1 |
| tracknetv2-efficient-shuttlecock-tracking | 81.4 | 80.6 | 89.4 |
| widely-applicable-strong-baseline-for-sports | 89.0 | 91.0 | 94.0 |
| widely-applicable-strong-baseline-for-sports | 82.8 | 81.7 | 90.3 |
| real-time-cnn-based-segmentation-architecture | 57.5 | 56.8 | 71.7 |
| widely-applicable-strong-baseline-for-sports | 31.6 | 35.1 | 46.7 |