Kinect v2 Based Real-Time Motion Comparison with Re-targeting and Color Code Feedback
Chuan‐Kai Yang, Richard Tondowidjojo · 2019
In this paper, we propose a system to evaluate a user's performance in a real-time manner. Kinect v2 is used to acquire a professional user's motion as a reference motion and a trainee user's motion as a query motion. By utilizing the open-end dynamic time warping algorithm, the system compares the pre-recorded reference motion with the query motion in real-time. The comparison result is shown to the user as a feedback by using a color-coded re-targeted 3D model.