Real-time event detection system for intelligent video surveillance

• Main Authors: Chua, Timothy John A., Co, Andrew Jonathan W., Ilustre, Paolo Javier S., Manzano, Enrique M., Lapira, Edzel R.
• Format: text
• Published: Animo Repository 2024
• Subjects: Video recordings > Production and direction; Video recordings industry; Surveillance radar; Electronic surveillance; Engineering
• Online Access: https://animorepository.dlsu.edu.ph/faculty_research/12173
• Institution: De La Salle University

The use of CCTV cameras in various locations brings about an increase in security and safety. Unfortunately, it is quite tedious to monitor 50-100 live feeds simultaneously and for extended periods of time. To solve this problem, the use of automated surveillance must be considered. In this undertaking, a proof-of-concept real-time event detection system is proposed. The system takes a live feed from an analog camera via an encoder connected to the USB port of a computer. Various image processing techniques are then applied to the frames in order to separate the foreground from the background. Useful information is subsequently extracted from the foreground and is used in identifying objects of interest, establishing object correspondence across consecutive frames and in analyzing the behavior of the object itself. Detected alarm events are noted by means of a log, which is visible through the user interface of the system.