Exploring Table Tennis Analytics: Domination, Expected Score and Shot Diversity - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Exploring Table Tennis Analytics: Domination, Expected Score and Shot Diversity

Résumé

Detailed sports data, including fine-grained player, ball positions, and action types, is becoming increasingly available thanks to advancements in sensor and video tracking technologies. In this study, we explore the potential of utilizing such data in table tennis to analyze player superiority, scoring opportunities, and creativity. Our approach involves adapting existing metrics by incorporating additional attributes provided by the detailed data, such as player zones and shot angles. Furthermore, we present a methodology for visualizing all metrics simultaneously during a single set, enabling a comprehensive assessment of their significance. We expect this approach to help for developing, comparing, and applying a broader range of metrics to table tennis and other racket sports. To facilitate further research and the benchmarking of novel metrics, we have made our code and dataset available as an open-source project.
Fichier principal
Vignette du fichier
_MLSA23__Analyzing_Table_Tennis_Games_using_Detailed_Sports_Data.pdf (654.15 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04240982 , version 1 (13-10-2023)

Identifiants

  • HAL Id : hal-04240982 , version 1

Citer

Gabin Calmet, Aymeric Erades, Romain Vuillemot. Exploring Table Tennis Analytics: Domination, Expected Score and Shot Diversity. Machine Learning and Data Mining for Sports Analytics, Sep 2023, Turin, Italy. ⟨hal-04240982⟩
81 Consultations
376 Téléchargements

Partager

Gmail Facebook X LinkedIn More