Piecewise linear prediction model for action tracking in sports - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Piecewise linear prediction model for action tracking in sports

Méthode de prédiction linéaire par morceaux pour le suivi d'action dans le sport

Résumé

Recent tracking methods in professional team sports reach very high accuracy by tracking the ball and players. However, it remains difficult for these methods to perform accurate real-time tracking in amateur acquisition conditions where the vertical position or orientation of the camera is not controlled and cameras use heterogeneous sensors. This article presents a method for tracking interesting content in an amateur sport game by analyzing player displacements. Defining optical flow of the foreground in the image as the player motions, we propose a piecewise linear supervised learning model for predicting the camera global motion needed to follow the action.
Fichier principal
Vignette du fichier
Action_Tracking.pdf (1.34 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03563325 , version 1 (09-02-2022)
hal-03563325 , version 2 (02-06-2022)

Identifiants

  • HAL Id : hal-03563325 , version 2

Citer

Axel Baldanza, Jean-François Aujol, Yann Traonmilin, François Alary. Piecewise linear prediction model for action tracking in sports. EUSIPCO 2022, Aug 2022, Belgrade, Serbia. ⟨hal-03563325v2⟩

Collections

CNRS IMB
74 Consultations
61 Téléchargements

Partager

Gmail Facebook X LinkedIn More