This project aimed to develop a football player tracking system using YOLOv5, an object detection model, and SORT, a multi-object tracking algorithm. The system was designed to track and analyze the movement of individual players on the field during a football match. The YOLOv5 model was used to detect and locate players in each frame of the video. The model was trained on a dataset of football players and was fine-tuned to achieve high accuracy in detecting players on the field. The SORT algorithm was then used to track the players over time. SORT is a Multi-Object Tracking (MOT) algorithm that uses data association and motion models to predict the location of each player in the next frame. The system was implemented using Python and the OpenCV library, which is commonly used for computer vision tasks. The system was tested on footage of real football matches, and the performance was evaluated using metrics such as accuracy, precision, and recall. This system can be used for a wide range of applications, including analyzing player performance, tactical analysis, and video scouting. It can also be used in broadcasting, where it can provide real-time statistics, and enhance the viewing experience of the audience.