What is a typical signalized intersection in a city? A pipeline for intersection data imputation from OpenStreetMap

TL;DR

This work addresses the lack of standardized methods for extracting signalized intersections from OpenStreetMap data by proposing the OSMint pipeline, an end-to-end tool that merges road segments, traffic signals, and turn restrictions into coherent intersection datasets. The approach identifies intersections, reconstructs accurate geometry, and imputes key attributes such as lane counts, turn connectivity, speed limits, and gradients, demonstrated on Salt Lake City. Key contributions include a practical pipeline, open-source implementation, and a dataset-generation framework that reveals the limits of current crowdsourced data while enabling more transferable transportation research. The results show alignment with ground-truth intersection structures and provide a foundation for standardized data pipelines in smart cities and transportation analysis.

Abstract

Signalized intersections, arguably the most complicated type of traffic scenario, are essential to urban mobility systems. With recent advancements in intelligent transportation technologies, signalized intersections have great prospects for making transportation greener, safer, and faster. Several studies have been conducted focusing on intersection-level control and optimization. However, arbitrarily structured signalized intersections that are often used do not represent the ground-truth distribution, and there is no standardized way that exists to extract information about real-world signalized intersections. As the largest open-source map in the world, OpenStreetMap (OSM) has been used by many transportation researchers for a variety of studies, including intersection-level research such as adaptive traffic signal control and eco-driving. However, the quality of OSM data has been a serious concern. In this paper, we propose a pipeline for effectively extracting information about signalized intersections from OSM and constructing a comprehensive dataset. We thoroughly discuss challenges related to this task and we propose our solution for each challenge. We also use Salt Lake City as an example to demonstrate the performance of our methods. The pipeline has been published as an open-source Python library so everyone can freely download and use it to facilitate their research. Hopefully, this paper can serve as a starting point that inspires more efforts to build a standardized and systematic data pipeline for various types of transportation problems.

Figures (12)

• Figure 1: Intersection points in a signalized intersection with 4 approaches (US Department of Transportation)
• Figure 2: Pipeline for Extracting Signalized Intersections from OSM
• Figure 3: An example of identifying a signalized intersection with its approaches.
• Figure 4: An example of recovering geometry for approaches
• Figure 5: Two examples demonstrating why we need to consider two types of angles