ROCO: A Roundabout Traffic Conflict Dataset

TL;DR

This paper introduces ROCO, a comprehensive real-world roundabout traffic conflict dataset collected via video analysis, providing valuable data for safety research and analysis of traffic conflicts and crashes.

Contribution

The paper presents a novel large-scale traffic conflict dataset at a roundabout, including manual annotations, trajectory data, and conflict taxonomy, enabling advanced safety analysis.

Findings

Failure to yield is the main cause of conflicts.

557 traffic conflicts and 17 crashes recorded.

Dataset will be publicly available for research.

Abstract

Traffic conflicts have been studied by the transportation research community as a surrogate safety measure for decades. However, due to the rarity of traffic conflicts, collecting large-scale real-world traffic conflict data becomes extremely challenging. In this paper, we introduce and analyze ROCO - a real-world roundabout traffic conflict dataset. The data is collected at a two-lane roundabout at the intersection of State St. and W. Ellsworth Rd. in Ann Arbor, Michigan. We use raw video dataflow captured from four fisheye cameras installed at the roundabout as our input data source. We adopt a learning-based conflict identification algorithm from video to find potential traffic conflicts, and then manually label them for dataset collection and annotation. In total 557 traffic conflicts and 17 traffic crashes are collected from August 2021 to October 2021. We provide trajectory data of the traffic conflict scenes extracted using our roadside perception system. Taxonomy based on traffic conflict severity, reason for the traffic conflict, and its effect on the traffic flow is provided. With the traffic conflict data collected, we discover that failure to yield to circulating vehicles when entering the roundabout is the largest contributing reason for traffic conflicts. ROCO dataset will be made public in the short future.