The Harsh Truth: Segment-Level Analysis of Harsh Driving Events in Milan Using Large-Scale Telematics, Street Networks, and Google Street View

2026-05-29

AI Summary

This study addresses the limitations of traditional traffic crash data—namely, their latency and incompleteness—which hinder fine-grained road safety interventions. For the first time at a megacity scale, it integrates telemetry from 4.2 million onboard units, TomTom traffic metrics, OpenStreetMap road network data, and semantic segmentation of Google Street View imagery (using the OneFormer model). Combining Mann-Whitney U tests with machine learning regression, the research uncovers associations between segment-level aggressive driving behavior and road environment characteristics in Milan. Findings indicate that wider lanes, higher densities of intersections or bus stops, and unobstructed visibility correlate with increased aggressive driving intensity. Conversely, physically separated bicycle lanes significantly reduce such behavior, whereas painted-only bike lanes are associated with a 19.5% increase, offering empirical support for context-sensitive road safety policies.

Abstract

Police-reported crash statistics remain the standard input for urban road-safety assessment, but their incompleteness and reporting lag limit their usefulness for timely, fine-grained intervention design. Harsh acceleration and braking events are widely used as surrogate safety indicators, but have so far been studied only in comparatively small urban samples. This study analyses harsh events across the urban road network of Milan, combining high-resolution telematics from more than 4.2 million vehicles equipped with On-Board Units, segment-level traffic metrics from TomTom, street-network and infrastructure attributes from OpenStreetMap, and visual streetscape features extracted from Google Street View via semantic segmentation using a OneFormer model. We employ an analytical framework combining non-parametric Mann--Whitney U tests of segment-feature distributions between high- and low-harshness groups with supervised machine-learning regressors. We find that, once exposure is controlled for, wider carriageways, crossings and transit stops, and more open visual fields (higher sky- and road-pixel proportions) are associated with higher harsh-event intensity, while denser built frontage is associated with lower intensity. Finally, the cycling-infrastructure case study identifies a gradient in harsh-event intensity across facility types: markings-only cycle lanes are associated with a 19.5% higher harshness score, and mixed-traffic configurations with an 11.5% higher score, relative to physically separated cycle paths, conditional on the included controls. These results support context-specific rather than uniform urban-safety interventions and illustrate how large-scale telematics combined with open geospatial and visual data can inform Vision Zero decision-making at the metropolitan scale.

Problem

• harsh driving events
• road safety
• urban road network
• surrogate safety indicators
• fine-grained intervention

Innovation

• large-scale telematics
• semantic segmentation
• street view analysis
• surrogate safety indicators
• urban road safety