Basketball Movements Recognition Using a Wrist Wearable Inertial Measurement Unit

The traditional basketball training is unable to be quantified and shared with others for it heavily relies on the coach's experience. In this paper, we develop an inertial measurement unit (IMU) to collect movement data of the basketball player and identify his postures, which helps improve the coach's guidance and the athletes' skills in a quality manner. Additionally, the IMU sensor is designed to recognize nine kinds of basic basketball movements, such as stand, walk, run, jump, in-situ dribble, dribble while walking, dribble while running, set shot, and jump shot. Experimentally, the IMU sensor is worn on the player's right wrist. Meanwhile, the player's movements are captured by the sports camera (GoPro Hero 6) for reference. Further, five features are extracted from y-axis acceleration (YAA) data and z-axis angular velocity (ZAAV) data for the analysis of basketball movements. Finally, a 98.9% accuracy rate of recognizing each basic basketball movement of one player is achieved by using a neural network algorithm.