<aside> <img src="/icons/info-alternate_green.svg" alt="/icons/info-alternate_green.svg" width="40px" />

Traditional handball analysis relies heavily on manual observation and basic statistics, limiting the depth of performance insights available to coaches and players. Inspired by the successful implementation of computer vision in football analytics, this project explores the application of advanced CV techniques to handball, aiming to revolutionize how we understand and analyze the game.

</aside>

Technologies

• OpenCV - Core computer vision library for image processing and video analysis
• YOLO (You Only Look Once) - Real-time object detection for player identification
• DeepSORT - Multi-object tracking algorithm for following players across frames
• PyTorch or TensorFlow - Deep learning frameworks for model training and inference
• MediaPipe - Google's framework for pose estimation and human detection