• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.9
• /
• pp.1183-1189
• /
• 2021

There have been recently an increasing number of people working out at home. However, many of them do not have face-to-face guidance from experts, so they cannot effectively correct their wrong pose. This may lead to strain and injury to those doing home training. To tackle this problem, this paper proposes a video data-based pose classification and correction system for home training. The proposed system classifies poses using the multi-layer perceptron and pose estimation model, and corrects poses based on joint angels estimated. A voting algorithm that considers the results of successive frames is applied to improve the performance of the pose classification model. Multi-layer perceptron model for post classification shows the highest accuracy with 0.9. In addition, it is shown that the proposed voting algorithm improves the accuracy to 0.93.

• Journal of Internet Computing and Services
• /
• v.24 no.4
• /
• pp.47-56
• /
• 2023

This paper presents an approach to exercise that utilizes motion capture through the Rokoko Smart Suit. With the emergence of Covid-19, physical fitness levels have declined due to restrictions on in-person fitness classes and gym closures. To maintain physical activity, many individuals have turned to mobile applications and streaming videos. However, home workouts often lack the motivation and experience found in gyms, classes, or community centers, particularly with the presence of coaches and instructors. Additionally, instructors find it challenging to convey precise postures to their online students, and vice versa. To address this issue, the researchers propose the use of a full-body tracking suit like the Rokoko Smart Suit, which enables instructors to present a more realistic approach to physical activity. The Rokoko Smart Suit offers a 3D view of the instructor, eliminating the limitations of camera scope when streaming on platforms like Zoom or MS Teams. This technology enhances the at-home workout experience, and the incorporation of 3D virtual reality features can further elevate the realism of a workout.