Recognition of Game Phases in Football by Using Team’s GNSS Tracking Data
Sammanfattning: Positional tracking data is widely used in football for performance analysis. Many teams use GNSS integrated wearable devices to track physical metrics. However, utilizing GNSS data for tactical analysis is not common practice today. This thesis project aims to examine if GNSS data can be used in recognizing game phases in football. To achieve this, a system for filtering predefined sequences of the game was developed. We achieved nearly 80% accuracy in finding events, and 53% accuracy for filters. After in-depth analysis, it was shown that with small adjustments in filters, accuracy for over 80% can be achieved. Potential for finding sequences for over 90% accuracy after further research, is believed to be possible. A system with high accuracy could be used to automatically generate specified video feedback, game statistics, and validate manually collected event data. This kind of system would significantly save time and resources for teams and sports analysts.
HÄR KAN DU HÄMTA UPPSATSEN I FULLTEXT. (följ länken till nästa sida)