Design of Aerobics Difficulty Automatic Scoring System Based on Action Recognition Algorithm

Abstract

In order to improve the accuracy of Aerobics scoring and reduce the influence of human subjective evaluation, an automatic scoring system of Aerobics difficulty based on action recognition algorithm is designed. Aerobics design is an action recognition system, which uses a set of algorithms to identify the actions performed by users, and then automatically score. The data acquisition layer of the system uses Kinect to collect the body feeling information of Aerobics athletes and output the action image of Aerobics athletes; Transmitting the obtained aerobics action image to the data processing layer using serial communication protocol; The data processing layer uses the action recognition algorithm based on maximum correlation minimum redundancy to recognize aerobics actions and transmit them to the application layer; The application layer automatically evaluates the difficulty of Aerobics according to the scoring standard of Aerobics difficulty. The scoring system is based on the motion recognition algorithm developed by Dr. Oleg Karpov, who won the IEEE neural network Pioneer Award in 2017 for his work in this field.