Smart Work Zone Control and Performance Evaluation Based on Trajectory Data

Xie, Yuanchang; Bhuyan, Zubin; Liu, Ruifeng; Liu, Benyuan (Ben) · 2024 · ROSA P / Massachusetts. Dept. of Transportation. Office of Transportation Planning

archive: archived pipeline: cataloged verified

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

Summary

This study addresses the critical need to improve traffic safety and operations in highway work zones, a sector where fatalities increased by 42% between 2013 and 2019. Traditional evaluation metrics, such as throughput and average speed, fail to capture individual driver behaviors like speed adjustments and lane-changing decisions, which are fundamental to crash causation. Motivated by anticipated increases in infrastructure projects, the research aims to quantify the impact of specific control strategies—taper length, transverse rumble strips, flashing speed limit signs, and portable changeable message signs—on driver behavior using high-resolution trajectory data. The researchers conducted field evaluations at two highway work zones in Massachusetts (Medford and Danvers) and utilized additional data from New Hampshire. Data collection employed ultrahigh-definition radar sensors to capture individual vehicle speed profiles over a 1,000-foot segment and thermal cameras to record video footage, particularly for nighttime conditions. The study developed artificial intelligence methods, specifically using YOLOv8 models, to extract vehicle trajectories and identify risky last-minute merging events from thermal videos. The experimental design compared various configurations, including normal versus longer taper lengths and the presence or absence of rumble strips, while also accounting for time-of-day variations. Regression and descriptive analyses revealed that transverse rumble strips and taper length did not have consistent or statistically significant impacts on approaching speeds or vehicle merges. In contrast, flashing speed limit signs and portable changeable message signs significantly encouraged early merging and reduced approaching speeds. The study also identified distinct behavioral patterns based on lighting conditions, finding that drivers tended to drive slower and merge later during nighttime work zones compared to daytime operations. The findings suggest that dynamic signage is more effective than static physical modifications like rumble strips or taper adjustments for influencing driver behavior in work zones. This research provides Massachusetts Department of Transportation with evidence-based guidance for optimizing work zone layouts and dynamic merge controls. Furthermore, the developed computer vision framework for trajectory extraction offers a scalable tool for analyzing traffic operations in other contexts, such as on-ramps and managed lane facilities, enhancing the broader field of intelligent transportation systems.

Key finding

Flashing speed limit signs and portable changeable message signs significantly encourage early merging and reduce approaching speeds, whereas transverse rumble strips and taper length do not show consistent statistically significant impacts on these behaviors.

Methodology

field_study

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. Discovered via bulk_ingest_rosap on 2026-05-23 (6 acquisition events logged).

Summary generated by qwen3.6-27b-prismaquant on 2026-06-10; verification: verified.

Topics

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

• work zones
• emergency work zone conspicuity
• perceptual countermeasures

Information type

What kind of knowledge this paper contributes, grouped by family — independent of topic (what it is about) and method (how it was studied).

• Methodological Resource: dataset resource