Published Paper Details:

In the constantly evolving realm of urban security, the incorporation of machine learning (ML) technologies into existing Closed-Circuit Television (CCTV) networks emerges as a game-changing solution. Inspired by real- world challenges where traditional surveillance methods often falter, our project sets out to redefine urban safety through innovative technological interventions. Our approach harness the potential of ML, involving the YOLOv8 (YOU ONLY LOOK ONCE) algorithm, to conduct real-time analysis of video feeds, swiftly identifying suspicious activities, anomalies, crowd congestion, weapons, and known criminal faces. By seamlessly integrating ML-generated insights with conventional surveillance techniques, we aim to elevate the public safety, enhance law enforcement efficiency, prevent crimes, and streamline operational processes. Additionally, our system leverages facial recognition capabilities to identify wanted individuals from a database of known criminals, further crime prevention efforts. Moreover, we incorporated a work monitoring module, for tracking employee presence, work utilization, and non-violent scenarios to optimize workplace safety. This initiative marks a significant milestone in urban security, laying the groundwork for safer and smarter cities in the future.