Tennis Motion Recognition. Design of Classification Approaches and Experimental Studies

This monograph presents studies concerning the challenging topic of Human Action Recognition, which has recently become of increasing importance to those working in the field of Computer Vision. It contains an overview of the research literature on tennis movements recognition based on video, ima...

全面介紹

Saved in:
書目詳細資料
主要作者: Skublewska-Paszkowska, Maria
格式: Online
語言:英语
出版: Lublin University of Technology Publishing House 2025
主題:
在線閱讀:https://directory.doabooks.org/handle/20.500.12854/160677
標簽: 添加標簽
沒有標簽, 成為第一個標記此記錄!
_version_ 1869516814062452736
author Skublewska-Paszkowska, Maria
author_browse Skublewska-Paszkowska, Maria
author_facet Skublewska-Paszkowska, Maria
author_sort Skublewska-Paszkowska, Maria
collection Directory of Open Access Books
description This monograph presents studies concerning the challenging topic of Human Action Recognition, which has recently become of increasing importance to those working in the field of Computer Vision. It contains an overview of the research literature on tennis movements recognition based on video, images, motion capture data, and data registered using various sensors. In this monograph, three novel methods of tennis movements recognition are presented in detail with success, achieving high performance of the proposed classifiers. They all utilize Graph Convolutional Neural networks (GCN) solutions. Two methods are also applied using attention modules which improve feature extraction and thus make the classification better. The Spatial- -Temporal Graph Convolutional Network, the Attention-Temporal Graph Convolutional Network and the Dual Attention Temporal Graph Convolutional Network are applied for recognition of the most frequently used tennis moves, such as: forehand, backhand, volley forehand, and volley backhand. Moreover, the forehand and backhand are further divided into two phases: 1) the preparation, starting from the player’s positioning until the moment just before the ball makes contact with the racket, 2) the hit together with the racket swinging until the move is finished. These separations allow detailed analysis. For the purpose of this study, a 3DTennisDS dataset was created that contains motion capture data of the forehand, backhand, volley forehand, and volley backhand. They were registered via the Vicon motion capture system. Three proposed neural networks methods were verified based on the gathered dataset. In this monograph, the interpretability aspect of GCN was also presented. This issue is important and was examined by presenting feature maps and heatmaps obtained after selected convolutional operations. These results showed how individual filters in GCNs extract features that are relevant for recognizing tennis movements.
format Online
id doab-20.500.12854ir-160677
institution Directory of Open Access Books
language eng
publishDate 2025
publishDateRange 2025
publishDateSort 2025
publisher Lublin University of Technology Publishing House
publisherStr Lublin University of Technology Publishing House
record_format ojs
spelling doab-20.500.12854ir-1606772025-06-03T13:20:21Z Tennis Motion Recognition. Design of Classification Approaches and Experimental Studies Skublewska-Paszkowska, Maria : Graph Neural Networks, tennis movements recognition, fuzzification, attention modules, interpretability thema EDItEUR::U Computing and Information Technology::UY Computer science::UYQ Artificial intelligence::UYQM Machine learning This monograph presents studies concerning the challenging topic of Human Action Recognition, which has recently become of increasing importance to those working in the field of Computer Vision. It contains an overview of the research literature on tennis movements recognition based on video, images, motion capture data, and data registered using various sensors. In this monograph, three novel methods of tennis movements recognition are presented in detail with success, achieving high performance of the proposed classifiers. They all utilize Graph Convolutional Neural networks (GCN) solutions. Two methods are also applied using attention modules which improve feature extraction and thus make the classification better. The Spatial- -Temporal Graph Convolutional Network, the Attention-Temporal Graph Convolutional Network and the Dual Attention Temporal Graph Convolutional Network are applied for recognition of the most frequently used tennis moves, such as: forehand, backhand, volley forehand, and volley backhand. Moreover, the forehand and backhand are further divided into two phases: 1) the preparation, starting from the player’s positioning until the moment just before the ball makes contact with the racket, 2) the hit together with the racket swinging until the move is finished. These separations allow detailed analysis. For the purpose of this study, a 3DTennisDS dataset was created that contains motion capture data of the forehand, backhand, volley forehand, and volley backhand. They were registered via the Vicon motion capture system. Three proposed neural networks methods were verified based on the gathered dataset. In this monograph, the interpretability aspect of GCN was also presented. This issue is important and was examined by presenting feature maps and heatmaps obtained after selected convolutional operations. These results showed how individual filters in GCNs extract features that are relevant for recognizing tennis movements. Published 2025-05-28T11:48:46Z 2025-05-28T11:48:46Z 2024 book 978-83-7947-608-4 https://directory.doabooks.org/handle/20.500.12854/160677 eng image/jpeg Attribution-ShareAlike 4.0 International https://rock.pollub.pl/entities/publication/7840fa8c-8eb9-4bbf-98b6-779e5ba20ecd Lublin University of Technology Publishing House Lublin University of Technology Publishing House 10.35784/9788379476084 10.35784/9788379476084 25440dcb-6509-4ffb-b078-818857fbed4b 978-83-7947-608-4 Lublin University of Technology Publishing House Lublin open access
spellingShingle : Graph Neural Networks, tennis movements recognition, fuzzification, attention modules, interpretability
thema EDItEUR::U Computing and Information Technology::UY Computer science::UYQ Artificial intelligence::UYQM Machine learning
Skublewska-Paszkowska, Maria
Tennis Motion Recognition. Design of Classification Approaches and Experimental Studies
title Tennis Motion Recognition. Design of Classification Approaches and Experimental Studies
title_full Tennis Motion Recognition. Design of Classification Approaches and Experimental Studies
title_fullStr Tennis Motion Recognition. Design of Classification Approaches and Experimental Studies
title_full_unstemmed Tennis Motion Recognition. Design of Classification Approaches and Experimental Studies
title_short Tennis Motion Recognition. Design of Classification Approaches and Experimental Studies
title_sort tennis motion recognition design of classification approaches and experimental studies
topic : Graph Neural Networks, tennis movements recognition, fuzzification, attention modules, interpretability
thema EDItEUR::U Computing and Information Technology::UY Computer science::UYQ Artificial intelligence::UYQM Machine learning
topic_facet : Graph Neural Networks, tennis movements recognition, fuzzification, attention modules, interpretability
thema EDItEUR::U Computing and Information Technology::UY Computer science::UYQ Artificial intelligence::UYQM Machine learning
url https://directory.doabooks.org/handle/20.500.12854/160677
work_keys_str_mv AT skublewskapaszkowskamaria tennismotionrecognitiondesignofclassificationapproachesandexperimentalstudies