Using iterated local alignment to aggregate trajectory data into a traffic flow map

2024-06-25

AI Summary

This paper addresses the low accuracy of road-level traffic flow mapping from vehicle trajectory data with geographic coordinates, primarily caused by measurement noise. To overcome this challenge, we propose an iterative local alignment method that leverages inferred road segment fragments as local references to progressively align neighboring road segments, enabling adaptive spatial matching and circumventing the limitations of conventional global matching approaches in fine-grained aggregation. Our core contributions include: (i) a road segment inference model, (ii) a local geometric alignment algorithm, and (iii) a multi-scale trajectory aggregation pipeline, integrated within a unified validation framework combining synthetic and real-world trajectory data. Experimental results demonstrate substantial improvements in both localization accuracy and spatial resolution of road-level traffic flow estimation, supporting high-fidelity static and interactive traffic mapping across multiple scales—from urban and regional levels down to individual road segments.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Intelligent Robots: Localization, Mapping, and Navigation
• Search and Optimization: Local Search

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Security and Privacy: Large-scale security measurements
• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications

Abstract

Vehicle trajectories, with their detailed geolocations, are a promising data source to compute traffic flow maps at scales ranging from the city/regional level to the road level. The main obstacle is that trajectory data are prone to measurement noise. While this is negligible for city level large-scale flow aggregation, it poses substantial difficulties for road level small-scale aggregation. To overcome these difficulties, we introduce innovative local alignment algorithms, where we infer road segments to serve as local reference segments, and proceed to align nearby road segments to them. We deploy these algorithms in an iterative workflow to compute locally aligned flow maps. By applying this workflow to synthetic and empirical trajectories, we verify that our locally aligned flow maps provide high levels of accuracy and spatial resolution of flow aggregation at multiple scales for static and interactive maps.

Problem

• Aggregating noisy vehicle trajectories into accurate traffic flow maps
• Overcoming measurement noise for road-level flow aggregation
• Enhancing spatial resolution in multi-scale static and interactive maps

Innovation

• Iterative local alignment for trajectory aggregation
• Road segments as local reference for alignment
• High accuracy multi-scale flow maps