Badminton Activity Recognition Using Accelerometer Data
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...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-08-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/17/4685 |
| _version_ | 1827708832118210560 |
|---|---|
| author | Tim Steels Ben Van Herbruggen Jaron Fontaine Toon De Pessemier David Plets Eli De Poorter |
| author_facet | Tim Steels Ben Van Herbruggen Jaron Fontaine Toon De Pessemier David Plets Eli De Poorter |
| author_sort | Tim Steels |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-10T17:10:21Z |
| format | Article |
| id | doaj.art-a166af4bd2b64062b4c7fd58bc9bb44e |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T17:10:21Z |
| publishDate | 2020-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-a166af4bd2b64062b4c7fd58bc9bb44e2023-11-20T10:40:49ZengMDPI AGSensors1424-82202020-08-012017468510.3390/s20174685Badminton Activity Recognition Using Accelerometer DataTim Steels0Ben Van Herbruggen1Jaron Fontaine2Toon De Pessemier3David Plets4Eli De Poorter5IDLab, Department of Information Technology, Ghent University-imec, 9000 Ghent, BelgiumIDLab, Department of Information Technology, Ghent University-imec, 9000 Ghent, BelgiumIDLab, Department of Information Technology, Ghent University-imec, 9000 Ghent, BelgiumWAVES, Department of Information Technology, Ghent University-imec, 9000 Ghent, BelgiumWAVES, Department of Information Technology, Ghent University-imec, 9000 Ghent, BelgiumIDLab, Department of Information Technology, Ghent University-imec, 9000 Ghent, BelgiumA 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.https://www.mdpi.com/1424-8220/20/17/4685badmintonactivity recognitionaccelerometergyroscopeDNNCNN |
| spellingShingle | Tim Steels Ben Van Herbruggen Jaron Fontaine Toon De Pessemier David Plets Eli De Poorter Badminton Activity Recognition Using Accelerometer Data Sensors badminton activity recognition accelerometer gyroscope DNN CNN |
| title | Badminton Activity Recognition Using Accelerometer Data |
| title_full | Badminton Activity Recognition Using Accelerometer Data |
| title_fullStr | Badminton Activity Recognition Using Accelerometer Data |
| title_full_unstemmed | Badminton Activity Recognition Using Accelerometer Data |
| title_short | Badminton Activity Recognition Using Accelerometer Data |
| title_sort | badminton activity recognition using accelerometer data |
| topic | badminton activity recognition accelerometer gyroscope DNN CNN |
| url | https://www.mdpi.com/1424-8220/20/17/4685 |
| work_keys_str_mv | AT timsteels badmintonactivityrecognitionusingaccelerometerdata AT benvanherbruggen badmintonactivityrecognitionusingaccelerometerdata AT jaronfontaine badmintonactivityrecognitionusingaccelerometerdata AT toondepessemier badmintonactivityrecognitionusingaccelerometerdata AT davidplets badmintonactivityrecognitionusingaccelerometerdata AT elidepoorter badmintonactivityrecognitionusingaccelerometerdata |