Yoga Pose Perfection using Deep Learning

Abstract
 Even with lots of attention and work in the computer vision artificial intelligence field, human body pose detection is still a daunting task. The application wide-ranging from health monitoring to public security. This paper focuses on yoga, an art that has been performed for over millennium. In modern society yoga become common method exercise there-in arises demand instructions how do properly. Doing certain postures improperly may lead injuries fatigue hence presence trainer becomes important. As many people don’t have resources instructor or guide, can act as substitute advise their poses. Currently, research surrounding estimation mainly discusses classification yogic this work, we propose method, using Tensorflow MoveNet Thunder model, allows real-time detect error person's pose, thereby allowing them correct it.