American Football Play Type and Player Position Recognition

• Published in: Electronics (Basel) 2024-09, Vol.13 (18), p.3628
• Main Authors: Hong, Audrey, Orr, Benjamin, Pan, Ephraim, Lee, Dah-Jye
• Format: Article
• Language: English
• Subjects: Algorithms; Automation; Cameras; Computer & video games; Computer vision; Data augmentation; Datasets; Experiments; Football; Football (College); Games; Machine learning; Neural networks; Occlusion; Performance evaluation; Players; Recognition; Soccer; Sports injuries; Strategic planning; Teams
• ISSN: 2079-9292; 2079-9292
• DOI: 10.3390/electronics13183628

American football is one of the most popular team sports in the United States. There are approximately 16,000 high school and 890 college football teams, and each team plays around 10–14 games per football season. Contrary to most casual fans’ views, American football is more than speed and power, it requires preparation and strategies. Coaches analyze hours of video of their own and opponents’ games to extract important information such as offensive play formations, personnel packages and opposing coaches’ tendency to gain competitive advantages. This time-consuming and slow process called “tagging” takes away the coaches’ time from other duties and limits the players’ time for preparation and training. In this work, we created three datasets for our experiments to demonstrate the importance of player detection accuracy, which is easily affected by camera placement and player occlusion issues. We applied a unique data augmentation technique to generate data for each specific experiment. Our model achieved a remarkable 98.52% accuracy in play type recognition and 92.38% accuracy in player position recognition for the experiment that assumes no missing players or no occlusion problem, which could be achieved by placing the camera high above the football field.