Football activities classification
Ahmed Mohamed Emam, Omar Tarek Ali, Ayman Atia · 2023
Football, also known as soccer in some regions, is a popular sport that requires teams to score more goals than each other to win. As the sport gains more popularity, people are increasingly interested in learning its techniques. This study proposes a system that can help users learn football techniques such as juggling, inside-of-the-foot pass, and fake shot double tap (drill), and this move is divided into two parts. The system offers real-time feedback on users' actions, allowing them to learn more effectively. To achieve this, the system uses Mediapipe, an open-source library, to extract the coordinates of the human skeleton from the video recorded by the user. Besides, four classification algorithms, namely dollarpy, KNN, RFE, and SVM, to classify the actions performed by the user. If the user performs any of the specified actions correctly, they are awarded one point, and at the end of the session, they receive a report indicating how many times they performed each action. System results show that the model was able to predict the actions with high accuracy. The accuracies reached by the models used RFE, SVM, KNN, and dollarpy were 80%, 90%, 75&, and 55% respectively.