Construction of an Accurate Tracking and Ai Evaluation System for Dance Movements by Incorporating Image Recognition Technology
, e
17 mar 2025
INFORMAZIONI SU QUESTO ARTICOLO
Pubblicato online: 17 mar 2025
Ricevuto: 05 nov 2024
Accettato: 10 feb 2025
DOI: https://doi.org/10.2478/amns-2025-0294
Parole chiave
© 2025 Jianchao Luan et al., published by Sciendo
This work is licensed under the Creative Commons Attribution 4.0 International License.
Figure 1.
Figure 2.
Figure 3.
Figure 4.
Figure 5.
Different characteristics of different human regions are extracted
| Body part | RGB | SIFT | Flow | SIFT=Flow |
|---|---|---|---|---|
| Upper body | 10.2 | 25.5 | 34.2 | 48.3 |
| Lower body | 10.5 | 26.2 | 34.7 | 48.0 |
| Upper body + lower body | 24.3 | 34.3 | 46.2 | 58.1 |
| Whole body | 22.8 | 31.7 | 41.7 | 55.8 |
The result of the dance movement
| Fragment number | Action description | Starting frame/one | End frame/one |
|---|---|---|---|
| ZT-01 | Bend your knees | 1 | 171 |
| ZT-02 | Big kick | 172 | 233 |
| ZT-03 | Winding | 234 | 296 |
| ZT-04 | Toe | 297 | 355 |
| ZT-05 | Bray | 356 | 399 |
| ZT-06 | Toe drawing | 400 | 519 |