i-manager Publications

Yoga Pose Classification using Resnet of Deep Learning Models

Lakshmi J. V. N. *, Chetan Kumar Bagaria**

*Sunstone Eduversity, Bangalore, Karnataka, India.

**Senior Application Developer, IBM, India.

Periodicity:June - August'2021
DOI : https://doi.org/10.26634/jcom.9.2.18464

Abstract

Yoga has got a plethora of health benefits which improves flexibility, perfects body posture, builds muscle strength, and increases focus. A model is designed to help the yoga practitioners to save money on trainers and be self-paced to practice in any time as per convenience. For any yoga pose, three levels of classification are considered. They are body position, variation in the body position, and the actual yoga posture. The model will be built using a building block based on a variation of ResNet. Yoga-82, is a hierarchically labelled dataset used to train the models. The developed model will be able to help a beginner to learn various levels of classification associated with a particular yoga pose. A developed model is presented, showing significant performance improvement over the past models built for tracking the fitness of the people and gave a significant boost to the yoga applications.

Keywords

Yoga, Deep Learning, Image Processing, Pose Detection, ResNet.

How to Cite this Article?

Lakshmi, J. V. N., and Bagaria, C. K. (2021). Yoga Pose Classification using Resnet of Deep Learning Models. i-manager's Journal on Computer Science, 9(2), 29-40. https://doi.org/10.26634/jcom.9.2.18464

References

[1]. Fu, R., Li, B., Gao, Y., & Wang, P. (2018). CNN with coarse-to-fine layer for hierarchical classification. IET Computer Vision, 12(6), 892-899.

[2]. He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 770-778).

[3]. Kendall, A., Grimes, M., & Cipolla, R. (2015). PoseNet: A convolutional network for real-time 6-dof camera relocalization. In Proceedings of the IEEE International Conference on Computer Vision (pp. 2938-2946).

[4]. Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems, 25, 1097-1105.

[5]. Ribani, R., & Marengoni, M. (2019, October). A survey of transfer learning for convolutional neural networks. In nd 2019, 32 SIBGRAPI Conference on Graphics, Patterns and Images Tutorials (SIBGRAPI-T) (pp. 47-57). IEEE.

[6]. Srivastava, N., & Salakhutdinov, R. R. (2013). Discriminative transfer learning with tree-based priors. Advances in Neural Information Processing Systems, 1-9.

[7]. Tan, M., & Le, Q. (2019, May). Efficientnet: Rethinking model scaling for convolutional neural networks. In International Conference on Machine Learning (pp. 6105-6114). PMLR.

[8]. Verma, M., Kumawat, S., Nakashima, Y., & Raman, S. (2020). Yoga-82: A new dataset for fine-grained classification of human poses. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops(pp. 1038-1039).

[9]. Yan, Z., Zhang, H., Piramuthu, R., Jagadeesh, V., DeCoste, D., Di, W., & Yu, Y. (2015). HD-CNN: Hierarchical deep convolutional neural networks for large scale visual recognition. In Proceedings of the IEEE international Conference on Computer Vision (pp. 2740-2748).

[10]. Zhu, X., & Bain, M. (2017). B-CNN: branch convolutional neural network for hierarchical classification. Cornell University (pp.1-9).

If you have access to this article please login to view the article or kindly login to purchase the article

Single Article

	North Americas,UK, Middle East,Europe		India	Rest of world
	USD	EUR	INR	USD-ROW
Online	15	15

ADD TO CART

Options for accessing this content:

If you would like institutional access to this content, please recommend the title to your librarian.
If you already have i-manager's user account: Login above and proceed to purchase the article.
New Users: Please register, then proceed to purchase the article.