AI-Driven Road Expansion Recommendation System Based on Vehicle Traffic Patterns

DOI

https://www.doi.org/10.59256/ijsreat.20260602010

Published In

Volume 6, Issue 2 (2026)

Published Online

March-April 2026

Pages

66-73

Article Type

Original Article

Check for updates

The urban transport systems are getting overwhelmed with the high population growth rate and the increase in the number of vehicles with congestion, wearing of the roads and less efficiency of the movements. To deal with this, we introduce an AI-based Road Expansion and Maintenance Recommendation System that can analyze the behavior of data and condition of pavements in real- time together. The model uses YOLOv8 to detect vehicles and road- damage in high speed, which is further improved using the ResNet50 to classify vehicles into fine-grain categories. In the meantime, Deep SORT provides identity-preserving multi-object tracking, which allows to estimate densities with precision over continuous frames. The carbon emission is also assessed on the basis of distribution of vehicles category in the framework to make sustainability-based decisions. Through traffic analytics and assessment of infrastructure, the system can produce automatic advice regarding road widening or high-priority road maintenance. The solution is built to be scalable and allows linking with smart cities and to plan urban infrastructures in a data-driven, proactive, and environmentally conscious way.