An Intelligent Video Surveillance System for Multi-Threat Detection and Real-Time Alerting

Abstract: Traditional CCTV surveillance systems rely heavily on continuous human monitoring, which is inefficient, error-prone, and unsuitable for large-scale deployment, as operators may miss critical events due to fatigue, overlapping camera feeds, poor lighting condi-tions, and the difficulty of tracking multiple screens simultaneously. To overcome these limitations, this paper presents an Intelligent Video Surveillance System (IVSS) capable of detecting multiple safety and security threats in real time. The proposed system integrates object detection, weapon detection, fire and smoke detection, fall detection, crash detection, and face recognition with watchlist matching into a unified pipeline. A YOLO-based model is employed for fast and accurate detection of persons and suspicious objects, while dedicated modules analyze fire patterns, abnormal human posture, sudden motion changes, and identity verification against a watchlist database. The system supports both live camera streams and recorded video input, making it flexible for various surveillance scenarios. To improve reliability and reduce false alarms, confidence-based filtering and temporal consistency checks across consecutive frames are applied before generating alerts. Detected incidents are stored as evidence in the form of annotated frames or video clips for further analysis. The modular architecture enables flexible deployment by allowing individual detection components to operate independently or as part of an integrated system. The proposed IVSS is well-suited for security-sensitive and safety-critical environments, providing en-hanced monitoring efficiency, reduced human workload, and faster response to potential threats.

Keywords: Intelligent Surveillance, YOLO, Face Recognition, Watchlist Matching, Fall Detection, Fire Detection, Real-Time Monitoring, Object Detection