YED-Net: Yoga Exercise Dynamics Monitoring with YOLOv11-ECA-Enhanced Detection and DeepSORT Tracking
Source abstract
Abstract
Against the backdrop of the deep integration of national fitness and sports science, this study addresses the lack of standardized movement assessment in yoga training by proposing an intelligent analysis system that integrates an improved YOLOv11-ECA detector with the DeepSORT tracking algorithm. A dynamic adaptive anchor mechanism and an Efficient Channel Attention (ECA) module are introduced, while the depthwise separable convolution in the C3k2 module is optimized with a kernel size of 2. Furthermore, a Parallel Spatial Attention (PSA) mechanism is incorporated to enhance multi-target feature discrimination. These enhancements enable the model to achieve a high detection accuracy of 98.6% mAP@0.5 while maintaining low computational complexity (2.35 M parameters, 3.11 GFLOPs). Evaluated on the SND Sun Salutation Yoga Dataset released in 2024, the improved model achieves a real-time processing speed of 85.79 frames per second (FPS) on an RTX 3060 platform, with an 18% reduction in computational cost compared to the baseline. Notably, it achieves a 0.9% improvement in AP@0.5 for small targets (<20 px). By integrating the Mars-smallCNN feature extraction network with a Kalman filtering-based trajectory prediction module, the system attains 58.3% Multiple Object Tracking Accuracy (MOTA) and 62.1% Identity F1 Score (IDF1) in dense multi-object scenarios, representing an improvement of approximately 9.8 percentage points over the conventional YOLO+DeepSORT method. Ablation studies confirm that the ECA module, implemented via lightweight 1D convolution, enhances channel attention modeling efficiency by 23% compared to the original SE module and reduces the false detection rate by 1.2 times under complex backgrounds. This study presents a complete “detection–tracking–assessment” pipeline for intelligent sports training. Future work aims to integrate 3D pose estimation to develop a closed-loop biomechanical analysis system, thereby advancing sports science toward intelligent decision-making paradigms.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Human Pose and Action Recognition · Anomaly Detection Techniques and Applications · Non-Invasive Vital Sign Monitoring
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Faculty of Applied Sciences, Macao Polytechnic University, Macao SAR, China
Department of Data Science, Beijing Institute of Technology, Zhuhai, Zhuhai 519088, China
State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing 100191, China
Department of Computer Science and Technology, Zhongfa Aviation Institute of Beihang University, 166 Shuanghongqiao Street, Pingyao Town, Yuhang District, Hangzhou 311115, China
Funding
Macao Polytechnic University
References (43)
Show source-provided references
1. The Health Benefits of Yoga and Exercise: A Review of Comparison Studies10.1089/acm.2009.0044 ↗
2. Insights on Surya Namaskar from Its Origin to Application Towards Health10.1016/j.jaim.2021.10.002 ↗
3. Exploring the Application of Artificial Intelligence in Sports Training: A Case Study Approach10.1155/2021/4658937 ↗
4. Zhang, L. (2022). Applying Deep Learning-Based Human Motion Recognition System in Sports Competition. Front. Neurorobot., 16.10.3389/fnbot.2022.860981 ↗
5. Verma, M., Kumawat, S., Nakashima, Y., and Raman, S. (2020, January 14–19). Yoga-82: A New Dataset for Fine-grained Classification of Human Poses. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, Seattle, WA, USA. Available online: https://api.semanticscholar.org/CorpusID:216056215.10.1109/CVPRW50498.2020.00527 ↗
6. Yadav, S.K., Shukla, A., Tiwari, K., Pandey, H.M., and Akbar, S.A. (2023). An Efficient Deep Convolutional Neural Network Model For Yoga Pose Recognition Using Single Images. arXiv, https://arxiv.org/abs/2306.15768.
7. Sharma, A., Sharma, P., Pincha, D., and Jain, P. (2022). Surya Namaskar: Real-time Advanced Yoga Pose Recognition and Correction for Smart Healthcare. arXiv, https://arxiv.org/abs/2209.02492.
8. Real-Time Digital Assistance for Exercise: Exercise Tracking System with MediaPipe Angle Directive Rules
9. Ravi, N., Gabeur, V., Hu, Y.-T., Hu, R., Ryali, C., Ma, T., Khedr, H., Rädle, R., Rolland, C., and Gustafson, L. (2024). Sam 2: Segment anything in images and videos. arXiv.
10. Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27–30). You Only Look Once: Unified, Real-Time Object Detection. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.91 ↗
11. Redmon, J., and Farhadi, A. (2017, January 21–26). YOLO9000: Better, Faster, Stronger. Proceedings of the 17 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.690 ↗
12. Redmon, J., and Farhadi, A. (2018). YOLOv3: An Incremental Improvement. arXiv, https://arxiv.org/abs/1804.02767.
13. Bochkovskiy, A., Wang, C.-Y., and Liao, H.-Y.M. (2020). YOLOv4: Optimal Speed and Accuracy of Object Detection. arXiv, https://arxiv.org/abs/2004.10934.
14. Jocher, G. (2020). Ultralytics YOLOv5, Version 7.0, Zenodo.
15. Li, C., Li, L., Jiang, H., Weng, K., Geng, Y., Li, L., Ke, Z., Li, Q., Cheng, M., and Nie, W. (2022). YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications. arXiv, https://arxiv.org/abs/2209.02976.
16. Wang, C.-Y., Bochkovskiy, A., and Liao, H.-Y.M. (2023, January 17–24). YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors. Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada.10.1109/CVPR52729.2023.00721 ↗
17. Jocher, G., Chaurasia, A., and Qiu, J. (2023). Ultralytics YOLOv8, Version 8.0.0., GitHub, Inc.. Available online: https://github.com/ultralytics/ultralytics.
18. Wang, C.-Y., Yeh, I.-H., and Liao, H.-Y.M. (2024). YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information. arXiv, https://arxiv.org/abs/2402.13616.10.1007/978-3-031-72751-1_1 ↗
19. Wang, A., Chen, H., Liu, L., Chen, K., Lin, Z., Han, J., and Ding, G. (2024). YOLOv10: Real-Time End-to-End Object Detection. arXiv, https://arxiv.org/abs/2405.14458.
20. Jocher, G., and Qiu, J. (2024). Ultralytics YOLO11, Version 11.0.0, GitHub, Inc.. Available online: https://github.com/ultralytics/ultralytics.
21. CCA-YOLO: Channel and Coordinate Aware-Based YOLO for Photovoltaic Cell Defect Detection in Electroluminescence Images10.1109/TIM.2025.3541805 ↗
22. Automatic Lane Discovery and Traffic Congestion Detection in a Real-Time Multi-Vehicle Tracking Systems10.1109/ACCESS.2024.3483439 ↗
23. Triangular Chain Closed-Loop Detection Network for Dense Pedestrian Detection
24. Pujara, A., and Bhamare, M. (2022, January 24–25). DeepSORT: Real-Time & Multi-Object Detection and Tracking with YOLO and TensorFlow. Proceedings of the 2022 International Conference on Augmented Intelligence and Sustainable Systems, Chennai, India.10.1109/ICAISS55157.2022.10011018 ↗
25. Wojke, N., Bewley, A., and Paulus, D. (2017, January 17–20). Simple Online and Realtime Tracking with a Deep Association Metric. Proceedings of the 2017 IEEE International Conference on Image Processing (ICIP), Beijing, China.10.1109/ICIP.2017.8296962 ↗
26. Dendorfer, P., Rezatofighi, H., Milan, A., Shi, J., Cremers, D., Reid, I., Roth, S., Schindler, K., and Leal-Taixé, L. (2020). MOT20: A Benchmark for Multi Object Tracking in Crowded Scenes. arXiv, https://arxiv.org/abs/2003.09003.
27. Enhancing Humanoid Robot Soccer Ball Tracking, Goal Alignment, and Robot Avoidance Using YOLO-NAS
28. Yoga Pose Estimation Using YOLO Model
29. Khanam, R., and Hussain, M. (2024). YOLOv11: An Overview of the Key Architectural Enhancements. arXiv, https://arxiv.org/abs/2410.17725.
30. End-to-End Semantic Segmentation Utilizing Multi-Scale Baseline Light Field10.1109/TCSVT.2024.3367370 ↗
31. Multimodal Perception Integrating Point Cloud and Light Field for Ship Autonomous Driving10.1109/TITS.2024.3381652 ↗
32. Pseudo 5D Hyperspectral Light Field for Image Semantic Segmentation10.1016/j.inffus.2025.103042 ↗
33. Tampering Localization and Self-Recovery Using Block Labeling and Adaptive Significance10.1016/j.eswa.2023.120228 ↗
34. PFPS: Polymerized Feature Panoptic Segmentation Based on Fully Convolutional Networks10.1109/TETCI.2024.3515004 ↗
35. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, Ł., and Polosukhin, I. (2023). Attention Is All You Need. arXiv, https://arxiv.org/abs/1706.03762.
36. Woo, S., Park, J., Lee, J.-Y., and Kweon, I.S. (2018). CBAM: Convolutional Block Attention Module. arXiv, https://arxiv.org/abs/1807.06521.10.1007/978-3-030-01234-2_1 ↗
37. Park, J., Woo, S., Lee, J.-Y., and Kweon, I.S. (2018). BAM: Bottleneck Attention Module. arXiv, https://arxiv.org/abs/1807.06514.
38. SimAM: A Simple, Parameter-Free Attention Module for Convolutional Neural Networks
39. Zhang, Q.-L., and Yang, Y.-B. (2021, January 6–11). SA-Net: Shuffle Attention for Deep Convolutional Neural Networks. Proceedings of the 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Toronto, ON, Canada.10.1109/ICASSP39728.2021.9414568 ↗
40. Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., and Hu, Q. (2020, January 14–19). ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Virtual Conference.10.1109/CVPR42600.2020.01155 ↗
41. Zhang, H., Zu, K., Lu, J., Zou, Y., and Meng, D. (2021). EPSANet: An Efficient Pyramid Squeeze Attention Block on Convolutional Neural Network. arXi, https://arxiv.org/abs/2105.14447.
42. Li, Y., Yan, H., Li, D., and Wang, H. (2024). Robust Miner Detection in Challenging Underground Environments: An Improved YOLOv11 Approach. Appl. Sci., 14.10.3390/app142411700 ↗
43. Lalitha (2024). Surya Namaskar Dataset (SND2024), Roboflow, Inc.. Available online: https://universe.roboflow.com/lalitha-uruu5/surya-namaskar.