Vision Based Automated Badminton Action Recognition Using the New Local Convolutional Neural Network Extractor

Rahmad, Nur Azmina; As’ari, Muhammad Amir; Ibrahim, Mohamad Fauzi; Sufri, Nur Anis Jasmin; Rangasamy, K S

doi:10.1007/978-981-15-3270-2_30

Cited by 11 publications

(9 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [ 17 ], a convolutional neural network delivers accuracies of up to 96.5% for their classification of tennis strokes. Finally, Reference [ 18 ] also uses a CNN, but this time by using visual recognition, achieving an accuracy around 98.7%.…”

Section: Related Workmentioning

confidence: 99%

Badminton Activity Recognition Using Accelerometer Data

Steels

Herbruggen

Fontaine

et al. 2020

Sensors

View full text Add to dashboard Cite

A thorough analysis of sports is becoming increasingly important during the training process of badminton players at both the recreational and professional level. Nowadays, game situations are usually filmed and reviewed afterwards in order to analyze the game situation, but these video set-ups tend to be difficult to analyze, expensive, and intrusive to set up. In contrast, we classified badminton movements using off-the-shelf accelerometer and gyroscope data. To this end, we organized a data capturing campaign and designed a novel neural network using different frame sizes as input. This paper shows that with only accelerometer data, our novel convolutional neural network is able to distinguish nine activities with 86% precision when using a sampling frequency of 50 Hz. Adding the gyroscope data causes an increase of up to 99% precision, as compared to, respectively, 79% and 88% when using a traditional convolutional neural network. In addition, our paper analyses the impact of different sensor placement options and discusses the impact of different sampling frequenciess of the sensors. As such, our approach provides a low cost solution that is easy to use and can collect useful information for the analysis of a badminton game.

show abstract

Section: Related Workmentioning

confidence: 99%

Badminton Activity Recognition Using Accelerometer Data

Steels

Herbruggen

Fontaine

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…In [ 87 ], a model is proposed to recognize two badminton action classes on match images: hit and non-hit, using a pre-trained AlexNet for features extraction and SVM for classification. Before using pre-trained AlexNet for automatic feature extraction, they have introduced a new local CNN extractor in the recognition pipeline.…”

Section: Har Implementation In Different Sportsmentioning

confidence: 99%

An overview of Human Action Recognition in sports based on Computer Vision

Host

Ivašić-Kos

2022

Heliyon

View full text Add to dashboard Cite

“…The models were used in a binary classification setting, to detect whether the player hit the shuttle or not. An extension was also proposed to use AlexNet as a feature extractor in combination with globally extracted features, which are then fed to a Support Vector Machine (SVM); this was tested in the binary case [8] and a 5-class stroke recognition problem [16].…”

Section: Related Workmentioning

confidence: 99%

“…Previous research in badminton stroke recognition can be divided into two broad families: methods focused on video and image analysis [7], [8] and methods based on wearable sensors [9], [10]. Although the latter involve the installation of specific sensors on the racket or the players' body, they also allow a more personalized analysis of the information.…”

Section: Introductionmentioning

confidence: 99%

Badminton stroke classification based on accelerometer data: from individual to generalized models

Peralta

Herbruggen

Fontaine

et al. 2022

2022 IEEE International Conference on Big Data (Big Data)

View full text Add to dashboard Cite

Activity recognition models based on wearable devices are becoming increasingly popular. However, models that are trained and tested on the same players show a large bias and are not generalizable to previously unseen players. In this paper, we tackle the badminton stroke recognition problem from this perspective, comparing the performance of individual and generalized models based on an accelerometer and a gyroscope, and identifying which components of the solution can maximize the performance of generalized models. First, we describe a simple convolutional neural network trained to classify 7 types of stroke. Second, the model is extended in a hybrid way to identify two additional classes (movement and rest). Third, data augmentation is applied on the training set. Fourth, transfer learning is applied to use data from the test player to fine-tune the generalized model and attempt to reach the performance of an individual model. These models are evaluated on a dataset collected from amateur players, both in a controlled environment and in a match simulation. The results showed a large difference between the performance of individual and generalized models; however, the latter could be improved by increasing the number of players in the training set, by data augmentation, and by transfer learning, highlighting the necessity of larger datasets in this field.

show abstract

Vision Based Automated Badminton Action Recognition Using the New Local Convolutional Neural Network Extractor

Cited by 11 publications

References 24 publications

Badminton Activity Recognition Using Accelerometer Data

Badminton Activity Recognition Using Accelerometer Data

An overview of Human Action Recognition in sports based on Computer Vision

Badminton stroke classification based on accelerometer data: from individual to generalized models

Contact Info

Product

Resources

About