EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Enhancing Yoga Pose Recognition through a Multimodal Hybrid Approach with Attention Mechanism and Late Fusion on Yoga For All-30

Jayasurya Marasani, Dhanvanth Reddy Yerramreddy, S Don

International Journal of Yoga · 2026-01 · 19 (1) · 72-84

DOI: 10.4103/ijoy.ijoy_11_25 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Yoga, online erschienen am 30.04.2026. Verfasst von Jayasurya Marasani und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science and Engineering, Amrita School of Computing, Amrita Vishwa Vidyapeetham, Kollam, Kerala, India. Die Arbeit nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Context

The project focuses on yoga pose recognition, a critical task in computer vision and AI, to enhance physical and mental well-being by improving posture analysis. It addresses challenges such as the lack of benchmark datasets and limitations in both landmark-augmented and landmark-free methods.

Aims

1. Developed a hybrid model combining landmark-based and landmark-free techniques for accurate yoga pose recognition 2. Introduced YFA-30, a comprehensive dataset with 30 yoga poses to benchmark pose recognition models 3. Conducted a comparative analysis of existing models with the proposed hybrid model. Settings and Design: The project operates within the domain of computer vision and artificial intelligence, specifically focusing on yoga pose recognition. It involves a controlled computational environment for training, validating, and testing deep learning models using datasets of yoga poses. The settings emphasize creating a system capable of real-time pose recognition and correction for practical applications in fitness, health, and education. Methods: • Hybrid Model: Combines MoveNet (landmark detection) and ResNet50 (image feature extraction) using a scaled dot-product attention mechanism and late fusion • Statistical Evaluation: Analyzes accuracy, loss, and performance metrics across multiple datasets (YFA-30, YFA-20, YFA-10, Kaggle, and Google CG) • Comparative Study: Benchmarks against models such as Mediapipe, YOLO-V8x, and Xception • Visualization: Uses Grad-CAM heatmaps for feature extraction insights. Material: Datasets: • YFA-30: Newly introduced dataset with 30 yoga poses with approximately 8000 images • Kaggle Dataset: Small dataset with 5 yoga poses • Google CG Dataset: Synthetic images of 5 yoga poses. Models: • Landmark-based: MoveNet, Mediapipe, and YOLO-V8x • Landmark-free: ResNet50, VGG16, EfficientNetB0, and Xception. Statistical Analysis Used: The statistical analyses used in your yoga pose recognition project include: 1. Performance Metrics: Accuracy, loss (training, validation, and test), and loss curves across datasets (YFA-30, YFA-20, YFA-10, Kaggle, and Google CG) to evaluate model efficiency 2. Comparative Analysis: Benchmarking the hybrid model (MoveNet + ResNet50) against other models such as Mediapipe, YOLO-V8x-pose, and landmark-free models (e.g., VGG16 and Xception) 3. Cross-Validation: Testing on YFA dataset subsets to ensure robustness across data variability 4. Attention Mechanism: Scaled dot-product attention and late fusion to integrate and prioritize relevant features and landmarks 5. Visual Analysis: Heatmaps (Grad-CAM) to interpret keypoint detection and feature extraction 6. Dataset Testing: Evaluation on synthetic and real-world datasets to ensure adaptability. These analyses validate the hybrid model’s performance and robustness.

Schlagwörter

Stichwörter der Autor:innen

Artificial intelligenceMoveNetResNet50attention mechanismdeep learninglate fusionyoga pose estimationyoga pose recognition

Autor:innen und Institutionen

  • Department of Computer Science and Engineering, Amrita School of Computing, Amrita Vishwa Vidyapeetham, Kollam, Kerala, India.
  • Department of Computer Science and Applications, Amrita School of Computing, Amrita Vishwa Vidyapeetham, Kollam, Kerala, India.

Zitieren

APA

Marasani, J., Yerramreddy, D. R., & Don, S. (2026). Enhancing Yoga Pose Recognition through a Multimodal Hybrid Approach with Attention Mechanism and Late Fusion on Yoga For All-30. International Journal of Yoga, 19(1), 72-84. https://doi.org/10.4103/ijoy.ijoy_11_25

Vancouver

Marasani J, Yerramreddy DR, Don S. Enhancing Yoga Pose Recognition through a Multimodal Hybrid Approach with Attention Mechanism and Late Fusion on Yoga For All-30. International Journal of Yoga. 2026;19(1):72-84. doi:10.4103/ijoy.ijoy_11_25

BibTeX
@article{Marasani2026,
  author = {Marasani, Jayasurya and Yerramreddy, Dhanvanth Reddy and Don, S},
  title = {Enhancing Yoga Pose Recognition through a Multimodal Hybrid Approach with Attention Mechanism and Late Fusion on Yoga For All-30},
  journal = {International Journal of Yoga},
  year = {2026},
  volume = {19},
  number = {1},
  pages = {72--84},
  doi = {10.4103/ijoy.ijoy_11_25}
}
Kostenlos starten →