Deep Learning Pose Estimation for Kinematics Measurement in Archery

Posture control is crucial in archery to achieve consistent and accurate arrow release on target shooting. Application of correct posture and joint motion can prevent undesired injuries and effectively reduces rapid fatigue in muscles. By using a markerless motion capture system, it can identify the posture and joint motion of archers between shooting performances and physical capacities with minimal interference on the archer. In this paper, a deep learning pose estimation approach is applied to retrieve joint information of an archer for in-depth posture and motion analysis. The posture of professional archers with average age of 17.3 are recorded as the samples of this study. Important parameters and joints, particularly the angles and its consistencies are analyzed to study archers shooting performances. In addition, an algorithm is proposed in this study to automate the determination of archer's anchoring and release sequence. Several qualitative results of joint kinematics and parameters and visualization are presented to further understand the bio-mechanical aspect of archery.