EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MA-Pose and DMMS-GCN: skeleton-based martial-arts category recognition with edge-device deployment

Longying Wang, Ruijie Zhang, Huiteng Xu, Shilin Guo

Frontiers in Neurorobotics · 04.11.2026 · 20

DOI: 10.3389/fnbot.2026.1967140 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Neurorobotics, online erschienen am 04.11.2026. Verfasst von Longying Wang und 3 weiteren Autor:innen. Die Arbeit nennt 63 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the development of visual sensor technology and human pose estimation algorithms, skeleton-based action recognition has received extensive attention in sports analysis and training systems. The recognition of martial-arts actions is difficult because different styles can share similar poses while differing in rhythm and coordination. To support this task, we constructed the Martial Arts Pose (MA-Pose) dataset, which contains 433 source videos across 13 martial arts categories. The 33-landmark sequences include normalized image coordinates and monocular relative depth rather than metric 3D ground truth. We further propose a Dynamic Multi-Stream Multi-Scale Graph Convolutional Network (DMMS-GCN), which integrates joint, bone, and motion features. The model combines physical, learnable, and input-adaptive graph topology with parallel temporal convolutions. With a fixed seed of 42, 346 videos are used for training and 87 for validation, with one center crop and one prediction per validation video. DMMS-GCN correctly classifies 73/87 videos (83.91% Top-1; 83.51% Macro-F1; 95% Wilson confidence interval, 74.78%–90.17%) and retrieves the correct class among the top five for 84/87 videos (96.55%). These values describe development-set performance because model selection and evaluation use the same validation subset. On a Raspberry Pi 4B, pose extraction runs at approximately 10 frames/s and classification of a prepared 150-frame tensor takes approximately 120 ms. Collecting the first 150 processed pose frames takes about 15 s, so the deployment demonstrates edge-device feasibility rather than instantaneous recognition. The source code, model checkpoint, and MA-Pose dataset are publicly available.

Zitieren

APA

Wang, L., Zhang, R., Xu, H., & Guo, S. (2026). MA-Pose and DMMS-GCN: skeleton-based martial-arts category recognition with edge-device deployment. Frontiers in Neurorobotics, 20. https://doi.org/10.3389/fnbot.2026.1967140

Vancouver

Wang L, Zhang R, Xu H, Guo S. MA-Pose and DMMS-GCN: skeleton-based martial-arts category recognition with edge-device deployment. Frontiers in Neurorobotics. 2026;20. doi:10.3389/fnbot.2026.1967140

BibTeX
@article{Wang2026,
  author = {Wang, Longying and Zhang, Ruijie and Xu, Huiteng and Guo, Shilin},
  title = {MA-Pose and DMMS-GCN: skeleton-based martial-arts category recognition with edge-device deployment},
  journal = {Frontiers in Neurorobotics},
  year = {2026},
  volume = {20},
  doi = {10.3389/fnbot.2026.1967140}
}
Kostenlos starten →