This project presents a computer vision system designed to analyze video footage of "8-Ball" billiard games. The system extracts high-level, real-time information about the game state, including the positions and trajectories of all balls on the table. These trajectories are visualized via a 2D top-down minimap, which is superimposed in the bottom-left corner of each video frame. The minimap offers an intuitive and continuous overview of ball dynamics, enhancing both analysis and viewer experience.
Fresco Eleonora, Girardello Sofia, Morselli Alberto
Date: July 2024
To look for all the output videos used as a test, check build/output
FinalProject/
├── build/ # Build directory for compiled files
└── output/ # Directory for output videos
├── res/ # Directory for resources
└── Dataset/ # Directory for datasets and sample videos
├── include/ # Header files
├── src/ # Source code files
├── LICENSE # License information
├── README.txt # Project overview
└── CMakeLists.txt # Build configuration
This project is licensed under the MIT License. See the LICENSE file for more details.