AR based Self-sports Learning System using Decayed Dynamic TimeWarping Algorithm

Abstract

A self-sports learning system that provides users with real-time multimodal feedback about differences between a user's motion and an expert's motion is proposed. We also propose the Decayed Dynamic Time Warping algorithm, which allows the user to change the motion speed dynamically and repeat a target motion without additional operations. The user can thus imitate an expert's motion conveniently and accurately. The proposed system involves training and replay modes. In the training mode, the system provides audio-visual feedback to help the user imitate the expert's motion. The replay mode allows the user to compare their motion to that of the expert. An augmented reality head-mounted display delivers feedback and provides an immersive three-dimensional training experience.