ANN-Enhanced IoT Wristband for Recognition of Player Identity and Shot Types Based on Basketball Shooting Motion Analysis

An IoT wristband for basketball shooting analysis, which can provide quantitative shooting guidance for basketball players in a convenient, low-cost manner, was developed. A micro inertial measurement unit (IMU) sensor-based wristband was used to collect the shooting motion data of 20 basketball players with different levels of skills: 15 amateur players and 5 elite players. The wristband was 247 mm
${}\times {}20$
mm
${}\times {}11$
mm in size, weighed 12.3 g, and consisted of a power system, a microcontroller, and an IMU sensor (MPU-9250), which can acquire the triaxial data of acceleration, angular velocity, and magnetic field data, and then transmit them to a computing platform via Bluetooth. After correlation analysis, the triaxial data of accelerations and angular velocities were used to identify these 18 shooting movements. Experimental results showed that the four categories of shooting movements (i.e., set shots, layups, jump shots, and tip-ins) could be recognized with an accuracy of 98.0%. The overall recognition accuracy of 18 kinds of shooting movements reached 98.5%. The AI wristband could also be used to distinguish the identity of the participants with a recognition rate of 97.4%. This new technology can be applied to quantitative basketball shot-making guidance and has potential applications for analyzing the motions of other sports such as table tennis, racquetball, volleyball, and soccer.