oguchi-ebube / action-recognition-soccer-players Goto Github PK
View Code? Open in Web Editor NEWA GUI which enables action classification and labelling of soccer player’s action in a broadcast video based on teams. Focus Areas: dribbling,kicking, running and passing using over 2000 sample images Methodology Create a flask application Connect to the User Interface(React) Use the trained model to process video frames Detect the skeleton(s) in each frame Label each detected skeleton(s) Give live analytics from the processing based on each team. Display the processed frames in a video format for the user. Get real-time action metrics for each team.