Football Penalty Kick Prediction Model Based on Kicker's Pose Estimation

Josue Angel Mauricio Salazar, Hugo Alatrista-Salas

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper describes an innovative methodology for predicting penalty kicks in football based on the pose estimation of the kicker. Our proposal starts with the construction of a corpus of penalty kick videos. Then, we combine semantic video segmentation and 3D pose estimation using the TAM and MMPose methods. For the prediction of the goal area where the kick would land, three deep-learning models were compared, as well as the study of the part of the player's body that affects the prediction task.

Original languageEnglish
Title of host publicationProceedings of the 2024 9th International Conference on Machine Learning Technologies, ICMLT 2024
PublisherAssociation for Computing Machinery
Pages196-203
Number of pages8
ISBN (Electronic)9798400716379
DOIs
StatePublished - 24 May 2024
Event9th International Conference on Machine Learning Technologies, ICMLT 2024 - Oslo, Norway
Duration: 24 May 202426 May 2024

Publication series

NameACM International Conference Proceeding Series

Conference

Conference9th International Conference on Machine Learning Technologies, ICMLT 2024
Country/TerritoryNorway
CityOslo
Period24/05/2426/05/24

Keywords

  • Computer Vision
  • Football
  • Human Pose Estimation
  • Video Segmentation

Fingerprint

Dive into the research topics of 'Football Penalty Kick Prediction Model Based on Kicker's Pose Estimation'. Together they form a unique fingerprint.

Cite this