Conference
Temporal Segmentation of Actions in Fencing Footwork Training
| العنوان: | Temporal Segmentation of Actions in Fencing Footwork Training |
|---|---|
| المؤلفون: | Malawski, Filip, Krupa, Marek |
| المساهمون: | Skala, Václav |
| بيانات النشر: | Václav Skala - UNION Agency |
| سنة النشر: | 2023 |
| المجموعة: | University of West Bohemia Digital Library / Digitální knihovna Západočeské univerzity v Plzni |
| مصطلحات موضوعية: | časová segmentace, rozpoznávání akcí, sportovní analýza, oplocení, odhad pozice, pohybová analýza, temporal segmentation, action recognition, sports analysis, fencing, pose estimation, motion analysis |
| الوصف: | The research presented in this paper was supported by the National Centre for Research and Development (NCBiR) under Grant No. LIDER/37/0198/L 12/20/NCBR/2021. We also thank Aramis Fencing School (aramis.pl) for providing experts’ consultations. ; Automatic analysis of actions in sports training can provide useful feedback for athletes. Fencing is one of the sports disciplines in which the correct technique for performing actions is very important. For any practical appli cation, temporal segmentation of movement in continuous training is crucial. In this work, we consider detecting and classifying actions in a sequence of fencing footwork exercises. We apply pose estimation to RGB videos and then we perform per-frame motion classification, using both classical machine learning and deep learning methods. Using sequences of frames with the same class we find data segments with specific actions. For evaluation, we provide extended manual labels for a fencing footwork dataset previously used in other works. Results indicate that the proposed methods are effective at detecting four footwork actions, obtaining 0.98 F1 score for recognition of action segments and 0.92 F1 score for per-frame classification. In the evaluation of our approach, we provide also a comparison with other data modalities, including depth-based pose estimation and inertial signals. Finally, we include an example of qualitative analysis of the performance of detected actions, to show how this approach can be used for training support. |
| نوع الوثيقة: | conference object |
| وصف الملف: | 8 s.; application/pdf |
| اللغة: | English |
| ردمك: | 978-80-86943-32-9 80-86943-32-1 |
| Relation: | WSCG 2023: full papers proceedings: 1. International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, p. 241-248.; 2464–4617 (print); 2464–4625 (CD/DVD); http://hdl.handle.net/11025/54430; https://www.doi.org/10.24132/CSRN.3301.28 |
| DOI: | 10.24132/CSRN.3301.28 |
| الاتاحة: | http://hdl.handle.net/11025/54430 https://doi.org/10.24132/CSRN.3301.28 |
| Rights: | © Václav Skala - UNION Agency ; openAccess |
| رقم الانضمام: | edsbas.D07C0E7B |
| قاعدة البيانات: | BASE |
| ردمك: | 9788086943329 8086943321 |
|---|---|
| DOI: | 10.24132/CSRN.3301.28 |