This project aims to develop a vision-based tracking system for humans. The system will be able to track humans in images and videos in real time and in video. It will use a combination of computer vision techniques, such as object detection, tracking, and background subtraction. The system will first detect humans in the scene using a deep sort learning model, such as YOLOv8. It will then track the detected humans using Kalman filter and deep sort algorithm. Finally, it will remove the background from the scene using background subtraction. The system will be evaluated on a dataset of images and videos containing humans. The system can be used for a variety of applications, such as surveillance, human-computer interaction, and robotics. It can be used to track people in crowded areas, to follow people's movements, and to interact with people in a natural way.