The aim of this project is to analyze a game of football using video feed from a camera. Finetuned versions of YOLOv10 are used to detect players and the ball. Using these detections, the game is analyzed to provide insights such as ball movement, team formation heatmaps, player statistics and passing opportunities.
pip install -r requirements.txt
SV_FT_WC14_kp
and SV_FT_WC14_lines
files from here and place them in the models folder.main.py
to perform detection and analysis on the video feed.Some videos with their detections have been provided in the results folder.