Object detection and tracking are widely utilized in today's society, especially for motion detection of different objects. The initial stage in object detection is to recognize objects in the video stream and cluster their pixels. The classification of an item is the next crucial step in tracking it. Computerized video surveillance, traffic monitoring, robotic vision, gesture recognition, human-computer interaction, military surveillance systems, vehicle navigation, medical imaging, biological image analysis, and many more areas may all benefit from object tracking. The goal of this project is to depict the different stages involved in object tracking in a video sequence, namely object detection, categorization, and tracking. This article compares different approaches for different stages of tracking and discusses several object identification and tracking methods.