Deep Learning-Based Yoga Posture Recognition Using the Y_PN-MSSD Model for Yoga Practitioners

Abstract

In today’s digital world, and in light of the growing pandemic, many yoga instructors opt to teach online. However, even after learning or being trained by the best sources available, such as videos, blogs, journals, or essays, there is no live tracking available to the user to see if he or she is holding poses appropriately, which can lead to body posture issues and health issues later in life. Existing technology can assist in this regard; however, beginner-level yoga practitioners have no means of knowing whether their position is good or poor without the instructor’s help. As a result, the automatic assessment of yoga postures is proposed for yoga posture recognition, which can alert practitioners by using the Y_PN-MSSD model, in which Pose-Net and Mobile-Net SSD (together named as TFlite Movenet) play a major role. The Pose-Net layer takes care of the feature point detection, while the mobile-net SSD layer performs human detection in each frame. The model is categorized into three stages. Initially, there is the data collection/preparation stage, where the yoga postures are captured from four users as well as an open-source dataset with seven yoga poses. Then, by using these collected data, the model undergoes training where the feature extraction takes place by connecting key points of the human body. Finally, the yoga posture is recognized and the model assists the user through yoga poses by live-tracking them, as well as correcting them on the fly with 99.88% accuracy. Comparatively, this model outperforms the performance of the Pose-Net CNN model. As a result, the model can be used as a starting point for creating a system that will help humans practice yoga with the help of a clever, inexpensive, and impressive virtual yoga trainer.

A Deep Learning Approach for Evaluating the Efficacy and Accuracy of PoseNet for Posture Detection

“…Furthermore, although the potential use cases of PoseNet in posture detection are generally recognized, there is a dearth of studies that conduct systematic assessments of its precision in various user demographics, environments, and postures (Brownlee, 2016). Considering the growing dependence on remote and virtual solutions for healthcare, tness, and interactive applications where precise and e cient posture detection is of the utmost importance; this gap is especially signi cant (Upadhyay et al, 2023).…”

Exploring the Use of Contrastive Language-Image Pre-Training for Human Posture Classification: Insights from Yoga Pose Analysis

“…With an ad hoc dataset of 187,200 low-resolution images created with the help of 18 volunteers doing 26 yoga poses, they achieved a 99.8% accuracy. In [27], the authors used images acquired by an RGB camera and an ad hoc CNN, created using Pose-Net and Mobile-Net SSD models, to recognize the postures. It reached an accuracy of 99.88%, although the dataset used for training and validation only contains 7 yoga positions.…”

“…The ultimate layer applies softmax activation to display the probability of each class. • Y_PN-MSSD [27] has an accuracy rate of 99.88% for a total of seven poses. The Y_PN-MSSD model architecture is a deep learning-based model that combines two components, namely PoseNet [34] and MobileNet SSD [35].…”

Development of Computer Vision-enabled Augmented Reality Games to Increase Motivation for Sports

“…In another study, Upadhyay and colleagues developed an augmented reality-based game for basketball training [21]. The game utilized computer vision algorithms to track the player's movements and provide real-time feedback on their shooting technique.…”