Yoga Pose Detection and Correction System

Abstract

Activity recognition is useful in many domains. These include biometrics, video -surveillance, human-computer interaction, assisted living, sports arbitration, in-home health monitoring, etc. The health status of an individual can be evaluated and predicted by monitoring and recognizing their activities. Yoga is one such domain that can be used to bring harmony to both body and mind with the help of asana, meditation, and various other breathing techniques. Nowadays in a fast-paced lifestyle, people do not have time to go to yoga classes. Hence, they prefer practicing yoga at home. However, there is a need for a tutor to assess their yoga poses. Hence, the system is presented where the user needs to do the yoga pose which is recognized in real-time video. Then, PoseNet is used to generate key points for the body parts. The identified pose is then compared with the target pose. Based on the comparison status generated by the function, verbal instructions are provided for the user to correct the yoga pose.