Posture Corrector: Incorrect Posture and Repetition Identifier using OpenPose and Deep Neural Network
Arata Maruhashi, Игорь Андреевич Гончаренко, Yanlei Gu · 2022 IEEE 4th Global Conference on Life Sciences and Technologies (LifeTech) · 2022
This paper suggests a software that can analyze a video that is recording a physical exercise and give a feedback to user according to their posture. OpenPose and user recorded video is used to extract body key points and this information are used to detect incorrect posture and detect start and end of the repetition. The software will use two different deep neural networks to identify whether the posture was correct or not for each repetition and gave feedback according to user’s posture at the end of analysis.