A fast deep learning based approach for basketball video analysis

Abstract

The aim of this study is to obtain an algorithm to analyze a basketball training in real time. That is, the approach should be able to detect the correct players and scores for each player. For this purpose, we first propose a method to detect the shots and if they are makes or misses. Specifically, we use a deep learning model to detect the position of the hoop and background subtraction to detect the shot. Then, scoring is determined by another neural network using classification. After the determination of the shot, we go back in our buffered images to find the player who sent the shot. The player is detected by YOLOv3-tiny and identified by a deep unsupervised reidentification model. To keep the real-time aim, all models employ mobile networks as base with different parameters and training methods. The experiments were conducted on two training videos. The experiment results show the effectiveness of the current method with over 95% accuracy on scoring identification and up to 91.4% overall accuracy on reidentification of 4 players in real-time. © 2020 ACM.