A fundamental task in computer vision and processing of the Image, with numerous applications across various domains: Including surveillance Webcams can be used for tracking objects or people in security systems. Webcams can track gestures and movements of objects, enabling interaction with computers without the need for traditional input devices. They can detect motion and track movement within a specified area. Object detection refers to the process of identifying and locating to detect objects which are seen in the image and video frame. This research focuses on detecting and tracking the objects, enabling the identification of specific objects across the consecutive frames. Object tracking maintains the identifying the individual objects across the multiple frames using the model CNN and R-CNN for the feature extraction. Motion detection is the typically process used to detect the movement of objects to identify the changes in current scene. This process involves the mathematical modeling and calculations to describe and predict an object's motion. The resulting trajectory represents the path that an object follows through space over time as it moves, often influenced by forces such as gravity. In essence, motion detection tracks dynamic changes, while the trajectory maps the continuous route of an object as it moves.