Enhancing Yoga Pose Estimation Accuracy Using Optimized Mask R-CNN Model

DOI

10.2991/978-94-6463-716-8_30How to use a DOI?

Keywords

Yoga Pose Estimation; Optimized Mask R-CNN; Key point Detection; Feature Aggregation; Human Pose Segmentation; Real-Time Fitness Tracking

Abstract

Yoga pose estimation is important for fitness, healthcare, and rehabilitation applications, existing models such as AlexNet, VGG, and ResNet cannot accurately recognize detailed key points or handle complex postures. To tackle these issues, this paper presents an improved mask R-CNN with better feature aggregation and segmentation and introduces a key point detection branch. Performance analysis demonstrates the effectiveness of our proposed model by improved values of mAP, AP@0. 5, and PCKh@0. 5 metrics. This approach has been experimentally shown to be used for real-time recovery from yoga poses. This work pushes forward the accuracy and scalability of pose estimation for widespread fitness and healthcare applications.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Deepak Shukla
AU  - Maya Rathore
PY  - 2025
DA  - 2025/05/26
TI  - Enhancing Yoga Pose Estimation Accuracy Using Optimized Mask R-CNN Model
BT  - Proceedings of the International Conference on Recent Advancements and Modernisations in Sustainable Intelligent Technologies and Applications (RAMSITA 2025)
PB  - Atlantis Press
SP  - 373
EP  - 384
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-716-8_30
DO  - 10.2991/978-94-6463-716-8_30
ID  - Shukla2025
ER  -