Classification of Tennis Actions Using Deep Learning
- URL: http://arxiv.org/abs/2402.02545v1
- Date: Sun, 4 Feb 2024 15:48:20 GMT
- Title: Classification of Tennis Actions Using Deep Learning
- Authors: Emil Hovad (1 and 2), Therese Hougaard-Jensen (2), Line Katrine Harder
Clemmensen (2) ((1) Alexandra Instituttet A/S, Rued Langgaards Vej 7, 2300
K{\o}benhavn S, Denmark, (2) Department of Mathematics and Computer Science,
Technical University of Denmark, Richard Petersens Plads, Building 324, 2800
Kgs. Lyngby, Denmark)
- Abstract summary: We investigate the potential and the challenges of using deep learning to classify tennis actions.
Three models of different size were trained and evaluated on the academic tennis dataset THETIS.
The best models achieve a generalization accuracy of 74 %, demonstrating a good performance for tennis action classification.
- Score: 0.0
- License: http://creativecommons.org/publicdomain/zero/1.0/
- Abstract: Recent advances of deep learning makes it possible to identify specific
events in videos with greater precision. This has great relevance in sports
like tennis in order to e.g., automatically collect game statistics, or replay
actions of specific interest for game strategy or player improvements. In this
paper, we investigate the potential and the challenges of using deep learning
to classify tennis actions. Three models of different size, all based on the
deep learning architecture SlowFast were trained and evaluated on the academic
tennis dataset THETIS. The best models achieve a generalization accuracy of 74
%, demonstrating a good performance for tennis action classification. We
provide an error analysis for the best model and pinpoint directions for
improvement of tennis datasets in general. We discuss the limitations of the
data set, general limitations of current publicly available tennis data-sets,
and future steps needed to make progress.
Related papers
- AI for Equitable Tennis Training: Leveraging AI for Equitable and Accurate Classification of Tennis Skill Levels and Training Phases [0.0]
The present study aims to classify tennis players' skill levels and classify tennis strokes into phases characterized by motion attributes.
We collected motion data, including Motion Yaw, Roll and Pitch from inertial measurement units (IMUs) worn by junior tennis players.
The SVM models demonstrated an overall accuracy of 77% in classifying players as beginners or intermediates.
arXiv Detail & Related papers (2024-06-24T03:40:41Z) - Zero-shot Retrieval: Augmenting Pre-trained Models with Search Engines [83.65380507372483]
Large pre-trained models can dramatically reduce the amount of task-specific data required to solve a problem, but they often fail to capture domain-specific nuances out of the box.
This paper shows how to leverage recent advances in NLP and multi-modal learning to augment a pre-trained model with search engine retrieval.
arXiv Detail & Related papers (2023-11-29T05:33:28Z) - Towards Active Learning for Action Spotting in Association Football
Videos [59.84375958757395]
Analyzing football videos is challenging and requires identifying subtle and diverse-temporal patterns.
Current algorithms face significant challenges when learning from limited annotated data.
We propose an active learning framework that selects the most informative video samples to be annotated next.
arXiv Detail & Related papers (2023-04-09T11:50:41Z) - Supervised Learning for Table Tennis Match Prediction [2.7835697868135902]
This paper proposes the use of machine learning to predict the outcome of table tennis single matches.
We use player and match statistics as features and evaluate their relative importance in an ablation study.
The results can serve as a baseline for future table tennis prediction models, and can feed back to prediction research in similar ball sports.
arXiv Detail & Related papers (2023-03-28T17:42:13Z) - Table Tennis Stroke Detection and Recognition Using Ball Trajectory Data [5.735035463793008]
A single camera setup positioned in the umpire's view has been employed to procure a dataset consisting of six stroke classes executed by four professional table tennis players.
Ball tracking using YOLOv4, a traditional object detection model, and TrackNetv2, a temporal heatmap based model, have been implemented on our dataset.
A mathematical approach developed to extract temporal boundaries of strokes using the ball trajectory data yielded a total of 2023 valid strokes.
The temporal convolutional network developed performed stroke recognition on completely unseen data with an accuracy of 87.155%.
arXiv Detail & Related papers (2023-02-19T19:13:24Z) - A Graph-Based Method for Soccer Action Spotting Using Unsupervised
Player Classification [75.93186954061943]
Action spotting involves understanding the dynamics of the game, the complexity of events, and the variation of video sequences.
In this work, we focus on the former by (a) identifying and representing the players, referees, and goalkeepers as nodes in a graph, and by (b) modeling their temporal interactions as sequences of graphs.
For the player identification task, our method obtains an overall performance of 57.83% average-mAP by combining it with other modalities.
arXiv Detail & Related papers (2022-11-22T15:23:53Z) - P2ANet: A Dataset and Benchmark for Dense Action Detection from Table Tennis Match Broadcasting Videos [64.57435509822416]
This work consists of 2,721 video clips collected from the broadcasting videos of professional table tennis matches in World Table Tennis Championships and Olympiads.
We formulate two sets of action detection problems -- emphaction localization and emphaction recognition.
The results confirm that TheName is still a challenging task and can be used as a special benchmark for dense action detection from videos.
arXiv Detail & Related papers (2022-07-26T08:34:17Z) - A Survey on Video Action Recognition in Sports: Datasets, Methods and
Applications [60.3327085463545]
We present a survey on video action recognition for sports analytics.
We introduce more than ten types of sports, including team sports, such as football, basketball, volleyball, hockey and individual sports, such as figure skating, gymnastics, table tennis, diving and badminton.
We develop a toolbox using PaddlePaddle, which supports football, basketball, table tennis and figure skating action recognition.
arXiv Detail & Related papers (2022-06-02T13:19:36Z) - Three-Stream 3D/1D CNN for Fine-Grained Action Classification and
Segmentation in Table Tennis [0.0]
It is applied to TT-21 dataset which consists of untrimmed videos of table tennis games.
The goal is to detect and classify table tennis strokes in the videos, the first step of a bigger scheme.
The pose is also investigated in order to offer richer feedback to the athletes.
arXiv Detail & Related papers (2021-09-29T09:43:21Z) - Table Tennis Stroke Recognition Using Two-Dimensional Human Pose
Estimation [0.0]
We introduce a novel method for collecting table tennis video data and perform stroke detection and classification.
A diverse dataset containing video data of 11 basic strokes obtained from 14 professional table tennis players has been collected.
A temporal convolutional neural network model developed using 2D pose estimation performs multiclass classification of these 11 table tennis strokes.
arXiv Detail & Related papers (2021-04-20T11:32:43Z) - PointContrast: Unsupervised Pre-training for 3D Point Cloud
Understanding [107.02479689909164]
In this work, we aim at facilitating research on 3D representation learning.
We measure the effect of unsupervised pre-training on a large source set of 3D scenes.
arXiv Detail & Related papers (2020-07-21T17:59:22Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.