Road-Eye:- A Real Time Traffic Monitoring System Using AI

– The rapid growth of urban populations has placed immense pressure on city traffic infrastructure, making real-time, intelligent monitoring a necessity rather than an option. Conventional signal control mechanisms, which operate on predetermined timing schedules, are inherently incapable of responding to the fluctuating demands of modern traffic. This paper introduces Road Eye, a decentralized, AI-powered traffic monitoring and adaptive signal control system that combines computer vision, edge computing, and Internet of Things (IoT) sensor networks into a cohesive operational framework. The architecture deploys deep learning object detection and multi-object tracking algorithms directly on edge devices positioned at intersections, enabling local video analysis without transmitting raw footage to central servers. Processed traffic metrics are relayed to a backend analytics module for dynamic signal phase optimization. System evaluation was conducted using SUMO-based traffic simulation across a representative urban intersection scenario. Experimental outcomes confirm a 38% reduction in average vehicle waiting time, a 40% decrease in queue length, and a fourfold improvement in signal response latency when compared to traditional fixed-time controllers. Road Eye offers a scalable, computationally efficient, and privacy-preserving solution for intelligent transportation infrastructure deployment in smart cities.