Model-based traffic state estimation using camera-equipped probe vehicles

TL;DR

This paper presents a novel, cost-effective traffic state estimation method using camera-equipped probe vehicles and advanced modeling techniques, demonstrating accurate density predictions from limited data in simulated environments.

Contribution

It introduces a new approach combining computer vision, Cell Transmission Model, and Genetic Algorithms for traffic estimation using partial trajectory data.

Findings

Accurately estimates traffic densities in unobserved regions.

Effective with limited data from simulated traffic scenarios.

Provides a high-resolution, cost-effective traffic monitoring solution.

Abstract

This study addresses the challenge of estimating traffic states for road links. We propose an innovative approach that leverages partial trajectory data captured by camera-equipped probe vehicles traveling in the opposite lane. The methodology combines state-of-the-art computer vision algorithms for extracting vehicle trajectories from street-view video sequences with a novel estimation technique based on the Cell Transmission Model (CTM) and Genetic Algorithms (GA). Our approach first calibrates Fundamental Diagram (FD) parameters using observed cell densities, then estimates boundary conditions for all space-time diagrams. We validate the method using simulated traffic data from three different types of links and parameter settings. Results show that the proposed methodology can estimate traffic densities in unobserved regions, even with limited data availability. This research contributes to the field by introducing a cost-effective, high-resolution traffic data collection method and a robust estimation technique for comprehensive traffic state information. While the study shows promising results, it also identifies areas for improvement, including refining models, optimizing processes, and testing with real-world data to enhance accuracy and scalability.