Automatic Detection of Faults in Simulated Race Walking from a Fixed Smartphone Camera
Automatic fault detection is a major challenge in many sports. In race walking, judges visually detect faults according to the rules. Hence, automatic fault detection systems will help a training of race walking without experts’ visual judgement. Some studies have attempted to use sensors and machin...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Sciendo
2024-02-01
|
| Series: | International Journal of Computer Science in Sport |
| Subjects: | |
| Online Access: | https://doi.org/10.2478/ijcss-2024-0002 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849738889935192064 |
|---|---|
| author | Suzuki Tomohiro Takeda Kazuya Fujii Keisuke |
| author_facet | Suzuki Tomohiro Takeda Kazuya Fujii Keisuke |
| author_sort | Suzuki Tomohiro |
| collection | DOAJ |
| description | Automatic fault detection is a major challenge in many sports. In race walking, judges visually detect faults according to the rules. Hence, automatic fault detection systems will help a training of race walking without experts’ visual judgement. Some studies have attempted to use sensors and machine learning to automatically detect faults. However, there are problems associated with sensor attachments and equipment such as a high-speed camera, which conflict with the visual judgement of judges, and the interpretability of the fault detection models. In this study, we proposed an automatic fault detection system for non-contact measurement. We used pose estimation and machine learning models trained based on the judgements of multiple qualified judges to realize fair fault judgement. We verified them using smartphone videos of normal race walking and walking with intentional faults in several athletes including the medalist of the Tokyo Olympics. The results show that the proposed system detected faults with an average accuracy of over 90%. We also revealed that the machine learning model detects faults according to the rules. In addition, the intentional faulty walking movement of the medalist was different from that of other walkers. This finding informs realization of a more general fault detection model. |
| format | Article |
| id | doaj-art-e7652b53c78f44bbaadc07c05d13cec6 |
| institution | DOAJ |
| issn | 1684-4769 |
| language | English |
| publishDate | 2024-02-01 |
| publisher | Sciendo |
| record_format | Article |
| series | International Journal of Computer Science in Sport |
| spelling | doaj-art-e7652b53c78f44bbaadc07c05d13cec62025-08-20T03:06:25ZengSciendoInternational Journal of Computer Science in Sport1684-47692024-02-01231223610.2478/ijcss-2024-0002Automatic Detection of Faults in Simulated Race Walking from a Fixed Smartphone CameraSuzuki Tomohiro0Takeda Kazuya1Fujii Keisuke2Graduate School of Informatics, Nagoya University, Nagoya, Aichi, JapanGraduate School of Informatics, Nagoya University, Nagoya, Aichi, JapanGraduate School of Informatics, Nagoya University, Nagoya, Aichi, JapanAutomatic fault detection is a major challenge in many sports. In race walking, judges visually detect faults according to the rules. Hence, automatic fault detection systems will help a training of race walking without experts’ visual judgement. Some studies have attempted to use sensors and machine learning to automatically detect faults. However, there are problems associated with sensor attachments and equipment such as a high-speed camera, which conflict with the visual judgement of judges, and the interpretability of the fault detection models. In this study, we proposed an automatic fault detection system for non-contact measurement. We used pose estimation and machine learning models trained based on the judgements of multiple qualified judges to realize fair fault judgement. We verified them using smartphone videos of normal race walking and walking with intentional faults in several athletes including the medalist of the Tokyo Olympics. The results show that the proposed system detected faults with an average accuracy of over 90%. We also revealed that the machine learning model detects faults according to the rules. In addition, the intentional faulty walking movement of the medalist was different from that of other walkers. This finding informs realization of a more general fault detection model.https://doi.org/10.2478/ijcss-2024-0002machine learningmotion analysisrace-walkingpose estimation |
| spellingShingle | Suzuki Tomohiro Takeda Kazuya Fujii Keisuke Automatic Detection of Faults in Simulated Race Walking from a Fixed Smartphone Camera International Journal of Computer Science in Sport machine learning motion analysis race-walking pose estimation |
| title | Automatic Detection of Faults in Simulated Race Walking from a Fixed Smartphone Camera |
| title_full | Automatic Detection of Faults in Simulated Race Walking from a Fixed Smartphone Camera |
| title_fullStr | Automatic Detection of Faults in Simulated Race Walking from a Fixed Smartphone Camera |
| title_full_unstemmed | Automatic Detection of Faults in Simulated Race Walking from a Fixed Smartphone Camera |
| title_short | Automatic Detection of Faults in Simulated Race Walking from a Fixed Smartphone Camera |
| title_sort | automatic detection of faults in simulated race walking from a fixed smartphone camera |
| topic | machine learning motion analysis race-walking pose estimation |
| url | https://doi.org/10.2478/ijcss-2024-0002 |
| work_keys_str_mv | AT suzukitomohiro automaticdetectionoffaultsinsimulatedracewalkingfromafixedsmartphonecamera AT takedakazuya automaticdetectionoffaultsinsimulatedracewalkingfromafixedsmartphonecamera AT fujiikeisuke automaticdetectionoffaultsinsimulatedracewalkingfromafixedsmartphonecamera |