Year: 2025
Type: article
Abstract: : Managing urban traffic efficiently has become a pressing challenge due to the increasing number of vehicles on the road. Traditional fixed-timing traffic systems fail to adapt to fluctuating traffic conditions, resulting in prolonged delays, unnecessary stops, and heightened environmental impact. Manual interventions by traffic personnel add to the inefficiency, demanding significant manpower while remaining static and error-prone. This project proposes a smart, AI-driven traffic management system which uses the YOLO model for real-time vehicle detection and density analysis. By dynamically adjusting signal durations based on vehicle flow, the system ensures optimal traffic movement, prioritizing heavily congested lanes. This adaptive approach reduces wait times, minimizes fuel consumption, and lowers emissions, addressing both commuter convenience and environmental sustainability. The system operates autonomously, eliminating human errors and reducing the need for manual control. It promotes smoother traffic flow, reduces operational costs, and improves safety for all road users. With its ability to respond to real-time data, this AI-powered traffic controller provides a transformative solution to urban traffic challenges, contributing to a more efficient and eco-friendly transportation ecosystem
Authors: Dr. Prakash N. Kalavadekar, Avanti Joshi, Vaishnavi Mohadkar, Pranjal Jagtap, Savari Jawale
Language: English
Subfield: Control and Systems Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W4408736987