From Sensors Data to Urban Traffic Flow Analysis

Po, Laura; Rollo, Federica; Bachechi, Chiara; Corni, Alberto · 2019 · Crossref

DOI: 10.1109/isc246665.2019.9071639

archive: archived pipeline: cataloged verified

Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)

Summary

This paper presents the implementation of an urban traffic flow model for Modena, Italy, as part of the TRAFAIR European project, which aims to correlate traffic data with air quality monitoring. The research addresses the growing challenge of urban pollution and congestion by leveraging real-time sensor data to create a dynamic simulation capable of estimating traffic flows across the entire city. The primary motivation is to provide a foundation for analyzing the impact of traffic on air quality and supporting smart city management decisions. The methodology integrates data from approximately 400 induction loop sensors, categorized into 345 urban sensors provided by the Municipality of Modena and 54 regional sensors provided by Lepida S.c.p.A. These sensors collect real-time data on vehicle counts, average speeds, and vehicle types. The road network was constructed using Open Street Map (OSM) data, which was filtered and manually enriched with lane counts and traffic restrictions to ensure accuracy. The simulation utilizes SUMO (Simulation of Urban Mobility), a microscopic traffic simulation tool. A key technical feature is the use of "calibrators" that dynamically adjust vehicle routes and speeds within the simulation to match real-time sensor inputs, ensuring the model reflects actual traffic conditions. The system automates the generation of input files from a PostgreSQL database and executes simulations on a High Performance Computing platform. The study demonstrates the model's ability to reproduce realistic traffic patterns, including morning peaks and congestion trends. By comparing simulation outputs with sensor data, the authors validated the model's reliability in estimating traffic density and flow across the urban network. The system generates detailed outputs, including vehicle counts and speeds for every road segment, allowing for the identification of congested areas and irregular traffic behaviors. The visualization tools developed enable the monitoring of traffic evolution over time, providing a comprehensive view of the city's mobility status. The significance of this work lies in its contribution to smart city infrastructure by providing a scalable, data-driven approach to traffic modeling. By accurately simulating urban traffic flows using real-time data, the model serves as a critical input for air quality forecasting and pollution analysis. This integration supports the broader goal of the TRAFAIR project to enhance citizen awareness and assist government decision-makers in managing urban environmental impacts. The paper establishes a framework for combining heterogeneous data sources—sensor data, OSM maps, and simulation tools—to create actionable insights for urban mobility and sustainability.

Provenance

The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed.

Summary generated by qwen3.6-27b-prismaquant on 2026-06-26; verification: verified.

Topics

Ranked by relevance to this paper. Hover a topic for its definition.

• traffic density