Research Area
Yoga Posture Recognition and Quantitative Evaluation with Wearable Sensors
Research Title
Yoga Posture Recognition and Quantitative Evaluation with Wearable Sensors Based on Two-Stage Classifier and Prior Bayesian Network.
Introduction
With the satisfaction of people’s material life, people are pursuing spiritual level and focusing on body health, and as a result, sports, like yoga and tai chi, have become essential activities in people’s daily life. Yoga is one of the most popular sports in the world, while the professional yoga instructors are only a very few. For most yoga amateurs, they could only learn yoga by self-study, like mechanically imitating from yoga video. In this way, it is difficult for the learner to observe the posture details of their whole body, since most postures require the learner to look at in a certain direction, and some postures even need the learner to lie on their stomach or back. As a result, they can not know whether they performed standardly or not. Consequently, it would cause low efficiency of learning. Hence, yoga posture recognition and evaluation are significant for guidance to self-study.
Yoga postures involve all parts of the body, which would increase the difficulty of posture acquisition and representation. Additionally, due to the large differences in the physical qualities of different trainers, such as flexibility of the body and ability to stretch the joints, the body shapes of different trainers performing the same yoga posture are also quite different. These differences greatly increase the difficulty of posture recognition. Previous human–robot interaction (HRI) research was mainly focused on posture recognition, while the posture evaluation was rarely studied. However, posture evaluation is significant in human sports as well. Posture evaluation could be used to find out about nonstandard parts of the body, which include misaligned limbs with respect to the standard posture model, such as the legs not being raised to the right height, the body not being stretched enough, or the joints not being maintained with the right angle.
Abstract
Currently, with the satisfaction of people’s material life, sports, like yoga and tai chi, have become essential activities in people’s daily life. For most yoga amateurs, they could only learn yoga by self-study, like mechanically imitating from yoga video. They could not know whether they performed standardly without feedback and guidance. In this paper, we proposed a full-body posture modeling and quantitative evaluation method to recognize and evaluate yoga postures to provide guidance to the learner. Back propagation artificial neural network (BP-ANN) was adopted as the first classifier to divide yoga postures into different categories, and fuzzy C-means (FCM) was utilized as the second classifier to classify the postures in a category. The posture data on each body part was regarded as a multidimensional Gaussian variable to build a Bayesian network. The conditional probability of the Gaussian variable corresponding to each body part relative to the Gaussian variable corresponding to the connected body part was used as criterion to quantitatively evaluate the standard degree of body parts. The angular differences between nonstandard parts and the standard model could be calculated to provide guidance with an easily-accepted language, such as “lift up your left arm”, “straighten your right forearm”. To evaluate our method, a wearable device with 11 inertial measurement units (IMUs) fixed onto the body was designed to measure yoga posture data with quaternion format, and the posture database with a total of 211,643 data frames and 1831 posture instances was collected from 11 subjects. Both the posture recognition test and evaluation test were conducted
Conclusion
In this paper, we proposed a full-body posture modeling and quantitative evaluation method to recognize and evaluate yoga postures and provide guidance to learner. BP-ANN and FCM were employed to construct a two-stage classifier to model and recognize full-body postures. BP-ANN was adopted as the first classifier to divide yoga postures into different categories due to its powerful nonlinear processing ability, and FCM was adopted as the second classifier to classify the postures in a category for the flexible fuzzy partition. The two-stage classifier could deal with the posture differences among subjects effectively and improve recognition results with low computing cost. In addition, we also proposed a recognition method to eliminate isolated recognised results and noisy results with cumulative probability, and further improve the recognition accuracy.
The quaternion data measured by IMU fixed on each body part was regarded as a multidimensional Gaussian variable to build a Bayesian network. The conditional probability of the Gaussian variable corresponding to each body part relative to the Gaussian variable corresponding to the connected body part was used to quantitatively evaluate the standard degree of the body part. Furthermore, guidance was provided to learner with an easily-accepted language, including correcting orientation and extent.
