Maqbullah, Afwatul (2025) Yoga posture recognition and classification using yolov5 / AFWATUL MAQBULLAH</p>. Diploma thesis, Universitas Negeri Malang.
Full text not available from this repository.Abstract
p Yoga a centuries-old health practice from India has gained widespread global recognition due to its benefits to physical mental and emotional well-being. As interest in yoga continues to grow so does the importance of ensuring proper pose execution. Despite its many advantages incorrect execution of yoga poses can lead to injuries or reduce the effectiveness of the practice. Addressing this challenge this research develops an automated system for recognizing and classifying yoga postures using YOLOv5 a state-of-the-art deep learning algorithm. YOLOv5 part of the YOLO (You Only Look Once) series is designed for real-time object detection and offers enhanced performance through features like anchor-free detection and adaptive training strategies making it an efficient and lightweight solution suitable for environments with limited resources. The study collects a dataset of 1 000 images across 20 yoga pose categories followed by manual annotation and training using transfer learning. The trained model demonstrated robust performance achieving an accuracy of 90% with precision and recall scores of 0.942 and 0.941 respectively and mAP 50 and mAP 50-95 values of 0.976 and 0.866. Compared to previous CNN-based approaches YOLOv5 offers higher speed and competitive accuracy making it well-suited for real-time applications. Although some poses showed lower accuracy due to dataset limitations performance may be improved through data augmentation or expanded training data. This system holds promise for AI-driven yoga education enabling practitioners to train independently with real-time feedback. /p
| Item Type: | Thesis (Diploma) |
|---|---|
| Divisions: | Fakultas Teknik (FT) > Departemen Teknik Elektro (TE) > S1 Teknik Elektro |
| Depositing User: | library UM |
| Date Deposited: | 01 Aug 2025 04:29 |
| Last Modified: | 09 Sep 2025 03:00 |
| URI: | http://repository.um.ac.id/id/eprint/399798 |
Actions (login required)
 |
View Item |