VR Alpine Ski Training Augmentation Using Visual Cues of Leading Skier

Erwin Wu, Takayuki Nozawa, Florian Perteneder, Hideki Koike; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2020, pp. 878-879

Alpine skiing has strong environmental dependencies and the way of teaching the movement is believed to be incremental and cyclical. Training alpine skiing on simulators is a challenging work, especially when supporting experienced learner to improve to higher level. In this paper, we propose several vision augmentations for learning from a recorded expert skier motion in the way to replay the motion as a virtual leading skier. The system uses an stationary indoor ski simulator and a VR System for prototyping, two VR trackers are used to capture the motion of skis so that users can control the skis on the virtual slope. For training, we captured the motion of professional athletes and replay it to let the users follow the experts in the slope. To support users, 6 different visual cues are introduced from different perspectives of learning skiing, such as the feet angle or the lateral position. To explore the utility of visual cues and to study how users could learn the motion patterns from the expert-skier effectively, we performed qualitative and quantitative evaluations. In addition, we also studied several visual feedback aiming to help the learning process. The work provides the basis for developing and understanding the possibilities and limitations of VR ski ski training, which also has the potential to be extended to AR/MR use in real world.