Name
Abstract | ||
|---|---|---|
In wheelchair basketball (WB), players are making efforts to improve the technique of wheelchair maneuver since it is the most basic and important action in every situation. However, the assessment of maneuver quality is difficult due to the lack of quantitative metrics. In this paper, in order to support the technical improvement of athletes in WB, we propose a maneuver classification method using inertial sensors. For this purpose, inertial sensors are fixed to the left and right axles of the wheelchair and the occurrence of maneuvers is detected using the angular velocity. Major maneuver activities in WB are classified into 2 types: PUSH and STOP. First, our method segments candidates of maneuver periods by the local maximum/minimum of the angular velocity since the rotation of the wheel generated by maneuvering leads to sharp changes of the angular velocity. Then, based on thresholds, we classify maneuver actions. For evaluation, we collected real data from 6 players. From the result, we confirmed our method achieves the average recall and precision of 88.0% and 87.6%, respectively. Furthermore, we confirmed the effectiveness of the classification results for the assessment of maneuver quality. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.23919/ICMU48249.2019.9006654 | 2019 Twelfth International Conference on Mobile Computing and Ubiquitous Network (ICMU) |
Keywords | DocType | ISBN |
Wheelchair basketball,sports data analysis,activity recognition | Conference | 978-1-7281-4226-5 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Ryosuke Hasegawa | 1 | 0 | 1.69 |
| Akira Uchiyama | 2 | 78 | 14.48 |
| Teruo Higashino | 3 | 1086 | 119.60 |