Abstract:
In this project, we study techniques for understanding video object motion activity which is becoming increasingly important with the widespread adoption of CCTV surveillance systems. This is more of importance nowadays in many surveillance systems used in Airports, Hotels, Clubs , High tech facilities and many other sensitive organisations that require a necessary need for security. We have peformed object detection and tracking in a live video feed for real time visual surveillance system for detecting and tracking multiple people and monitoring their activities. We are focusing on detection and tracking of multiple moving objects in live video feed coming from moving camera.The thesis present you with a unique technique of extraction and detection of motion and then track them down through a live video feed. Methods used for this technique is optical flow and is used for tracking objects , separating them from other taking all other multiple detections and view them through a moniter display. Results demonstrate a significant improvement in tracking, results can be made through the incorporation of the additional motion information.
