Gesture Analysis for Yoga Alignment (GAYA)
Paula Seffens1, Nataly Gonzalez1, William Seffens2
(1) Department of Health & Physical Education, University of North Georgia, Oakwood, GA.
(2) Physiology Department, Morehouse School of Medicine, Atlanta, GA.
Introduction
Yoga Therapy research has recently become the focus of rigorous scientific inquiry to understand and quantify its benefits for a wide variety of medical conditions. There remains health disparity between population segments who can readily access yoga classes and therapies. For difficult to reach individuals, yoga in an exergame format could be utilized in clinical or home environments. Objective of this study is to analyze yoga posture alignment using a gesture analysis program to produce a yoga exergame using the Microsoft Kinect sensor. We captured five yoga postures demonstrated by an advanced yoga teacher, as a gold standard for comparison purposes.
Purpose
The purpose of this research is to utilize existing gesture analysis software to provide skill improvement feedback to students in a college Yoga course setting.
AIM 1: To measure yoga posture alignment over the course of a 10-week period to provide objective feedback toward the goal of improved posture alignment.
AIM 2: To improve balance and kinesthetic awareness utilizing noninvasive measurements via an x, y, and z-point skeletal joint measurement platform.
AIM 3: To provide a hands on research experience for our Graduate Student Assistant in the department of Health & Physical Activity.
Results and Discussion
Convenience sample of undergraduate students with various levels of yoga experience, was recorded executing the same five postures at the first, middle and final yoga class session. Based on preliminary results the greater the self-rated yoga experience level, the higher the gesture score. Higher gesture scores are closer postures to the “gold standard” (obtained by capturing the postures performed by yoga instructors). Because of the limited sample size it is difficult to conclude the accuracy of the VisualGestureBuilder program in determining the statistical confidence of the study participants experience with yoga. However, because of the inherent differences in participant’s ability to perform yoga at a beginning skill level, the study should yield useful measurements of the skill growth as students learn yoga.
Gesture analysis for yoga alignment training may be a useful tool for the development of home and clinical yoga therapy for hard to reach populations. The Kinect sensor provides a tool that could score the performance of yoga therapy and provide quantitate measures of posture adherence and improvement. Our future plans to increase the sample size, study the potential effects of body mass and age on posture alignment, and assess breathing, heart rate and limb stretch.