Year: 2026
Type: article
Abstract: The congestion experienced in the world cities is a menace that is pushing cities to incur long travel time, fuel usage, and pollution. Conventional traffic management systems do not have the flexibility necessary to react to changing conditions of traffic in real-time, which worsens the congestion of the busiest periods and unexpected delays. The present paper offers a real-time traffic flow prediction framework that is to be used to overcome these issues by combining drones’ technology with adaptive signal control. This system tracks traffic in real-time based on aerial footage of drones and uses the state of the art object detector, YOLOv8, and supplementary ground-level data is obtained via the Google Maps API. A combination of these sources of data creates a multi-level picture of the traffic situation. A regression model is used to forecast the best traffic light times based on real-time data, which allows dynamic control of the signals, depending on the density of the traffic flowing. This system operates on a Raspberry Pi 5 with exact location readings of a GPS module mounted to the drone and constantly manipulates signal timing to reduce traffic jams and increase traffic speed. It combines advanced AI, drone surveillance, and predictive modelling, which can provide a solution to the urgent problem of more efficient management of urban traffic.
Institution: Vellore Institute of Technology University
Language: English
Subfield: Building and Construction
Field: Engineering
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $2,400
OpenAlex ID: W7214578901