A Recognition Method of Basketball’s Shooting Trajectory Based On Transfer Learning

Due to the low recognition accuracy and slow convergence speed of the traditional basketball shooting trajectory recognition methods, this paper proposes a basketball shooting trajectory recognition method based on transfer learning to accurately analyze the behavior pattern of shooting trajectory in the monitoring scene. The improved Hough method is used to obtain the basketball position, combined with the basketball speed, the cerebellar model neural network is constructed, the recursive unit is added with the recursive neural network, and then the variable weight is designed to improve the network structure. Combined with transfer learning, the speed of improving network optimization is accelerated, the missing information is made up, and the recognition of basketball shooting trajectory is realized. Experiments show that this method can accurately identify the basketball shooting trajectory with the minimum coordinate error, effectively improve the accuracy and time of network training, and improve the convergence speed and recognition accuracy.