Shot detection using skeleton position in badminton videos

Yoshikawa, Yui; Shishido, Hidehiko; Suita, Masashi; Kameda, Yoshinari; Kitahara, Itaru

doi:10.1117/12.2590407

Cited by 10 publications

(6 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Chu and Situmeang [6] developed an interface illustrating court detection, shot type classification, and offensive/defensive classification results from the given video. Yoshikawa et al [48] incorporates skeleton information to detect the timing of the overhead stroke by their collected videos with specialized cameras. To broaden the availability of videos to the general matches, an automatic annotation framework was designed to detect players from the official broadcast videos without special cameras or additional sensors [12].…”

Section: Related Workmentioning

confidence: 99%

ShuttleSet: A Human-Annotated Stroke-Level Singles Dataset for Badminton Tactical Analysis

Wang

Huang

İk

et al. 2023

Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

With the recent progress in sports analytics, deep learning approaches have demonstrated the effectiveness of mining insights into players' tactics for improving performance quality and fan engagement. This is attributed to the availability of public groundtruth datasets. While there are a few available datasets for turnbased sports for action detection, these datasets severely lack structured source data and stroke-level records since these require highcost labeling efforts from domain experts and are hard to detect using automatic techniques. Consequently, the development of artificial intelligence approaches is significantly hindered when existing models are applied to more challenging structured turn-based sequences. In this paper, we present ShuttleSet, the largest publiclyavailable badminton singles dataset with annotated stroke-level records. It contains 104 sets, 3,685 rallies, and 36,492 strokes in 44 matches between 2018 and 2021 with 27 top-ranking men's singles and women's singles players. ShuttleSet is manually annotated with a computer-aided labeling tool to increase the labeling efficiency and effectiveness of selecting the shot type with a choice of 18 distinct classes, the corresponding hitting locations, and the locations of both players at each stroke. In the experiments, we provide multiple benchmarks (i.e., stroke influence, stroke forecasting, and movement forecasting) with baselines to illustrate the practicability of using ShuttleSet for turn-based analytics, which is expected to stimulate both academic and sports communities. Over the past two years, a visualization platform has been deployed to illustrate the variability of analysis cases from ShuttleSet for coaches to delve into players' tactical preferences with human-interactive interfaces, which was also used by national badminton teams during multiple international high-ranking matches.

show abstract

Section: Related Workmentioning

confidence: 99%

ShuttleSet: A Human-Annotated Stroke-Level Singles Dataset for Badminton Tactical Analysis

Wang

Huang

İk

et al. 2023

Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

show abstract

“…Paper "Shot detection using skeleton position in badminton videos (2021)" proposed a shot detection method using the poses of a player in a badminton video sequence. In this method, the hit timing is detected by focusing on the arm movements of the player and analyzing the swing movement using skeletal information [14]. and another paper called Vision Based Automated Badminton Action Recognition Using the New Local Convolutional Neural Network Extractor (2020) proposed automated badminton action recognition from the computer vision data inputs using the deep learning pre-trained AlexNet Convolutional Neural Network (CNN) for features extraction and classify the features using supervised machine learning method which is linear Support-Vector Machine (SVM) and achieved an accuracy of 98.7% [15].…”

Section: Literature Reviewmentioning

confidence: 99%

AI-powered Badminton Video Detection: Enhancing Gameplay Analysis and Training

2023

JRAR

View full text Add to dashboard Cite

This research focuses on the use of AI-powered badminton video analysis to enhance gameplay analysis and training. The technology utilizes artificial intelligence and machine learning algorithms to analyze varJaccard Similarity Index aspects of badminton game footage, including player movements, shot selection, and game strategy. It provides personalized feedback and recommendations for improvement to players and helps coaches identify patterns and trends in their players' performance. The use of lightweight models, such as YoloV5, is essential for real-time video analysis due to the need for high-speed processing. These models, including MobileNets, EfficientNets, SqueezeNet, ShuffleNet, and Tiny-YOLO, are designed to be lightweight and optimized for speed while maintaining high accuracy. The Yolo model, a one-shot learning model, is particularly suitable for real-time object detection tasks due to its impressive speed and accuracy. It uses anchor boxes and data augmentation techniques to quickly learn and recognize objects with a high level of accuracy. The research process involved the collection of badminton match videos, preparation of datasets, and testing of the YoloV5 model's performance. Precision and Jaccard Similarity Index metrics using Jaccard similarity were used to evaluate the model's performance in detecting player positions and court boundaries. The results showed that the YoloV5 model performed better when tested on the video data with less clear image of judges in the background. The Jaccard Similarity Index metrics using Jaccard similarity demonstrated improved performance when tested on generalized video data was used to accurately evaluate the overlap between predicted and ground truth Overall, AI-powered badminton video analysis has the potential to revolutionize the way badminton is played and coached. The use of lightweight models like YoloV5 enables faster and more efficient real-time analysis, making it practical for a wide range of applications in badminton.

show abstract

“…2011-2016 2017-present Football [37]- [42] [30], [43]- [52] Basketball [53]- [59] [60]- [72] Volleyball [73]- [77] [78]-[83] Hockey [84]- [89] [90]-[99] Diving [100] [101]-[107] Tennis [108]- [113] [114]- [123] Table tennis [124]- [129] [130]-[138] Gymnastics [139]- [144] [145]-[148] Badminton [149]- [154] [155]- [164] Figure Skating [165], [166] [2], [167]- [174] Recently, researchers in the communities of computer vision and sports pay much attention to sports video analysis, including building datasets and proposing novel methodologies [2], [17]- [30]. In most existing works on sports video analysis, recognizing the actions of players in videos is crucial.…”

Section: Sportmentioning

confidence: 99%

A Survey on Video Action Recognition in Sports: Datasets, Methods and Applications

Wu¹,

Wang²,

Bian³

et al. 2022

Preprint

View full text Add to dashboard Cite

To understand human behaviors, action recognition based on videos is a common approach. Compared with imagebased action recognition, videos provide much more information. Reducing the ambiguity of actions and in the last decade, many works focused on datasets, novel models and learning approaches have improved video action recognition to a higher level. However, there are challenges and unsolved problems, in particular in sports analytics where data collection and labeling are more sophisticated, requiring sport professionals to annotate data. In addition, the actions could be extremely fast and it becomes difficult to recognize them. Moreover, in team sports like football and basketball, one action could involve multiple players, and to correctly recognize them, we need to analyse all players, which is relatively complicated. In this paper, 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, tennis, diving and badminton. Then we compare numerous existing frameworks for sports analysis to present status quo of video action recognition in both team sports and individual sports. Finally, we discuss the challenges and unsolved problems in this area and to facilitate sports analytics, we develop a toolbox using PaddlePaddle 1 , which supports football, basketball, table tennis and figure skating action recognition.

show abstract

Shot detection using skeleton position in badminton videos

Cited by 10 publications

References 0 publications

ShuttleSet: A Human-Annotated Stroke-Level Singles Dataset for Badminton Tactical Analysis

ShuttleSet: A Human-Annotated Stroke-Level Singles Dataset for Badminton Tactical Analysis

AI-powered Badminton Video Detection: Enhancing Gameplay Analysis and Training

A Survey on Video Action Recognition in Sports: Datasets, Methods and Applications

Contact Info

Product

Resources

About