An IMU-Based Approach to High Accuracy Real-Time Activity Recognition of Aerobic Boxing

There are one million members of fitness sports in Taiwan. During the epidemic of COVID-19, they cannot enjoy fitness activity under the guidance of coaches as usual. Under the individual guidance of digital coaches, anytime and anyplace to enjoy safe sports seem to be the future trend. Therefore, this paper proposes an approach based on high-precision real-time motion recognition to digital coaches for aerobic boxing. Boxer wears two bracelets to interact with the coach. Through the embedding of inertial sensors and high-efficient micro-controller on the bracelet, the proposed approach meets the needs of everyone to instantly identify the correctness of actions when exercising alone. To evaluate the performance of the proposed approach, two activities such as swing boxing and hook boxing are verified. Numeric results show that the recognition accuracy of 93% and 85.71% is for swing boxing and hook boxing, respectively.