Estimating player positions from padel high-angle videos: Accuracy comparison of recent computer vision methods

The estimation of player positions is key for performance analysis in sport. In this paper, we focus on image-based, single-angle, player position estimation in padel. Unlike tennis, the primary camera view in professional padel videos follows a de facto standard, consisting of a high-angle shot at...

Descripción completa

Detalles Bibliográficos
Autores: Javadiha, Mohammadreza|||0000-0002-4867-1132, Lacasa Claver, Enrique, Ric Díez, Angel, Andújar Gran, Carlos Antonio|||0000-0002-8480-4713, Susín Sánchez, Antonio|||0000-0002-0874-2784
Tipo de recurso: artículo
Fecha de publicación:2021
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/345963
Acceso en línea:https://hdl.handle.net/2117/345963
https://dx.doi.org/10.3390/s21103368
Access Level:acceso abierto
Palabra clave:Computer vision
Paddle tennis
Neural networks (Computer science)
Sports science
Racket sports
Deep learning
Pose estimation
Player tracking
Tracking data
Visió per ordinador
Pàdel
Xarxes neuronals (Informàtica)
Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Processament de la imatge i del senyal vídeo
id ES_1bb51ae24afc8dd4cc8cbc58df00c230
oai_identifier_str oai:upcommons.upc.edu:2117/345963
network_acronym_str ES
network_name_str España
repository_id_str
spelling Estimating player positions from padel high-angle videos: Accuracy comparison of recent computer vision methodsJavadiha, Mohammadreza|||0000-0002-4867-1132Lacasa Claver, EnriqueRic Díez, AngelAndújar Gran, Carlos Antonio|||0000-0002-8480-4713Susín Sánchez, Antonio|||0000-0002-0874-2784Computer visionPaddle tennisNeural networks (Computer science)Sports scienceRacket sportsDeep learningPose estimationPlayer trackingTracking dataVisió per ordinadorPàdelXarxes neuronals (Informàtica)Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Processament de la imatge i del senyal vídeoThe estimation of player positions is key for performance analysis in sport. In this paper, we focus on image-based, single-angle, player position estimation in padel. Unlike tennis, the primary camera view in professional padel videos follows a de facto standard, consisting of a high-angle shot at about 7.6 m above the court floor. This camera angle reduces the occlusion impact of the mesh that stands over the glass walls, and offers a convenient view for judging the depth of the ball and the player positions and poses. We evaluate and compare the accuracy of state-of-the-art computer vision methods on a large set of images from both amateur videos and publicly available videos from the major international padel circuit. The methods we analyze include object detection, image segmentation and pose estimation techniques, all of them based on deep convolutional neural networks. We report accuracy and average precision with respect to manually-annotated video frames. The best results are obtained by top-down pose estimation methods, which offer a detection rate of 99.8% and a RMSE below 5 and 12 cm for horizontal/vertical court-space coordinates (deviations from predicted and ground-truth player positions). These results demonstrate the suitability of pose estimation methods based on deep convolutional neural networks for estimating player positions from single-angle padel videos. Immediate applications of this work include the player and team analysis of the large collection of publicly available videos from international circuits, as well as an inexpensive method to get player positional data in amateur padel clubs.This work has been partially funded by the Spanish Ministry of Economy and Competitiveness and FEDER under grant TIN2017-88515-C2-1-R.Peer ReviewedMultidisciplinary Digital Publishing Institute (MDPI)20212021-05-1220212021-05-20journal articlehttp://purl.org/coar/resource_type/c_6501VoRhttp://purl.org/coar/version/c_970fb48d4fbd8a85info:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/2117/345963https://dx.doi.org/10.3390/s21103368reponame:UPCommons. Portal del coneixement obert de la UPCinstname:Universitat Politècnica de Catalunya (UPC)InglésengAgencia Estatal de Investigación http://doi.org/10.13039/501100011033 Plan Estatal de Investigación Científica y Técnica y de Innovación 2013-2016 TIN2017-88515-C2-1-R VISUALIZACION, MODELADO, SIMULACION E INTERACCION CON MODELOS 3D. APLICACIONES EN CIENCIAS DE LA VIDA Y ENTORNOS RURALES Y URBANOSopen accesshttp://purl.org/coar/access_right/c_abf2Attribution 4.0 Internationalhttps://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessoai:upcommons.upc.edu:2117/3459632026-05-27T15:37:01Z
dc.title.none.fl_str_mv Estimating player positions from padel high-angle videos: Accuracy comparison of recent computer vision methods
title Estimating player positions from padel high-angle videos: Accuracy comparison of recent computer vision methods
spellingShingle Estimating player positions from padel high-angle videos: Accuracy comparison of recent computer vision methods
Javadiha, Mohammadreza|||0000-0002-4867-1132
Computer vision
Paddle tennis
Neural networks (Computer science)
Sports science
Racket sports
Deep learning
Pose estimation
Player tracking
Tracking data
Visió per ordinador
Pàdel
Xarxes neuronals (Informàtica)
Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Processament de la imatge i del senyal vídeo
title_short Estimating player positions from padel high-angle videos: Accuracy comparison of recent computer vision methods
title_full Estimating player positions from padel high-angle videos: Accuracy comparison of recent computer vision methods
title_fullStr Estimating player positions from padel high-angle videos: Accuracy comparison of recent computer vision methods
title_full_unstemmed Estimating player positions from padel high-angle videos: Accuracy comparison of recent computer vision methods
title_sort Estimating player positions from padel high-angle videos: Accuracy comparison of recent computer vision methods
dc.creator.none.fl_str_mv Javadiha, Mohammadreza|||0000-0002-4867-1132
Lacasa Claver, Enrique
Ric Díez, Angel
Andújar Gran, Carlos Antonio|||0000-0002-8480-4713
Susín Sánchez, Antonio|||0000-0002-0874-2784
author Javadiha, Mohammadreza|||0000-0002-4867-1132
author_facet Javadiha, Mohammadreza|||0000-0002-4867-1132
Lacasa Claver, Enrique
Ric Díez, Angel
Andújar Gran, Carlos Antonio|||0000-0002-8480-4713
Susín Sánchez, Antonio|||0000-0002-0874-2784
author_role author
author2 Lacasa Claver, Enrique
Ric Díez, Angel
Andújar Gran, Carlos Antonio|||0000-0002-8480-4713
Susín Sánchez, Antonio|||0000-0002-0874-2784
author2_role author
author
author
author
dc.subject.none.fl_str_mv Computer vision
Paddle tennis
Neural networks (Computer science)
Sports science
Racket sports
Deep learning
Pose estimation
Player tracking
Tracking data
Visió per ordinador
Pàdel
Xarxes neuronals (Informàtica)
Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Processament de la imatge i del senyal vídeo
topic Computer vision
Paddle tennis
Neural networks (Computer science)
Sports science
Racket sports
Deep learning
Pose estimation
Player tracking
Tracking data
Visió per ordinador
Pàdel
Xarxes neuronals (Informàtica)
Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Processament de la imatge i del senyal vídeo
description The estimation of player positions is key for performance analysis in sport. In this paper, we focus on image-based, single-angle, player position estimation in padel. Unlike tennis, the primary camera view in professional padel videos follows a de facto standard, consisting of a high-angle shot at about 7.6 m above the court floor. This camera angle reduces the occlusion impact of the mesh that stands over the glass walls, and offers a convenient view for judging the depth of the ball and the player positions and poses. We evaluate and compare the accuracy of state-of-the-art computer vision methods on a large set of images from both amateur videos and publicly available videos from the major international padel circuit. The methods we analyze include object detection, image segmentation and pose estimation techniques, all of them based on deep convolutional neural networks. We report accuracy and average precision with respect to manually-annotated video frames. The best results are obtained by top-down pose estimation methods, which offer a detection rate of 99.8% and a RMSE below 5 and 12 cm for horizontal/vertical court-space coordinates (deviations from predicted and ground-truth player positions). These results demonstrate the suitability of pose estimation methods based on deep convolutional neural networks for estimating player positions from single-angle padel videos. Immediate applications of this work include the player and team analysis of the large collection of publicly available videos from international circuits, as well as an inexpensive method to get player positional data in amateur padel clubs.
publishDate 2021
dc.date.none.fl_str_mv 2021
2021-05-12
2021
2021-05-20
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
VoR
http://purl.org/coar/version/c_970fb48d4fbd8a85
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://hdl.handle.net/2117/345963
https://dx.doi.org/10.3390/s21103368
url https://hdl.handle.net/2117/345963
https://dx.doi.org/10.3390/s21103368
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.relation.none.fl_str_mv Agencia Estatal de Investigación http://doi.org/10.13039/501100011033 Plan Estatal de Investigación Científica y Técnica y de Innovación 2013-2016 TIN2017-88515-C2-1-R VISUALIZACION, MODELADO, SIMULACION E INTERACCION CON MODELOS 3D. APLICACIONES EN CIENCIAS DE LA VIDA Y ENTORNOS RURALES Y URBANOS
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Multidisciplinary Digital Publishing Institute (MDPI)
publisher.none.fl_str_mv Multidisciplinary Digital Publishing Institute (MDPI)
dc.source.none.fl_str_mv reponame:UPCommons. Portal del coneixement obert de la UPC
instname:Universitat Politècnica de Catalunya (UPC)
instname_str Universitat Politècnica de Catalunya (UPC)
reponame_str UPCommons. Portal del coneixement obert de la UPC
collection UPCommons. Portal del coneixement obert de la UPC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869404181306015744
score 15.301603

Similares en LA Referencia