AUTOMATED SURVELLIANCE AND MONITORING SYSTEM USING MACHINE LEARNING

Abstract

Automated surveillance and monitoring systems are important for maintaining security in crowded public places such as railway stations, airports, shopping malls, and event venues. Traditional CCTV systems rely on human operators to continuously watch multiple video feeds, which can lead to fatigue, distraction, and missed incidents. Because of this, suspicious activities or security threats may not be detected in time.To address this problem, this project proposes an Automated Surveillance and Monitoring System using the YOLO (You Only Look Once) object detection model. The system processes live CCTV video streams and uses YOLO to detect objects such as people, vehicles, and suspicious items in real time. Detected objects are highlighted with bounding boxes, making it easier to monitor activities and identify unusual situations such as unattended objects or unauthorized access.When suspicious activity is detected, the system generates instant alerts for security personnel, allowing quick response to potential threats. By automating object detection and monitoring using YOLO, the system reduces human workload and improves the efficiency and accuracy of surveillance in public areas.