Automated video analytics system for football matches.
XDSOFT, with the support of the Federal State Budgetary Institution "Fund for Assistance to Small Innovative Enterprises in the Scientific and Technical Sphere" (Innovation Assistance Fund), as part of the "Development-Artificial Intelligence" competition (IV stage), has developed an Automated Video Analytics System for football matches.
As a result of the project, new software was developed, a new dataset was created, and a new product was launched.
The Automated Video Analytics System for football matches provides tools for analyzing games, viewing player positions and match results, and comparing various metrics. It helps coaches, analysts, and scouts analyze and gather detailed information about matches and players.
The system's functionality includes the following capabilities:
- Detection and tracking of players and the ball on the field.
- Identification of player teams.
- Tracking players to determine their position on the field.
- Creation of heat maps showing player presence density in different field zones.
- Recognition of key game moments, such as goals, shots, passes, and other significant events.
- Performance metrics for players, such as speed and acceleration on the field.
The system uses neural networks and other machine learning algorithms. This significantly simplifies the analysis process and saves time for coaches, analysts, and scouts, who no longer have to spend hours manually analyzing matches.
The annual subscription cost is 60,000 RUB (excluding VAT).
Lifecycle Support Description.pdf