RoundaboutHD: High-Resolution Real-World Urban Environment Benchmark for Multi-Camera Vehicle Tracking

2025-07-11

AI Summary

Existing MCVT datasets suffer from simplistic scenes, low resolution, and limited environmental diversity, hindering cross-camera vehicle tracking research under realistic urban traffic conditions. To address this, we introduce RingTrack—the first high-resolution multi-camera vehicle tracking benchmark specifically designed for roundabout scenarios. It comprises 40 minutes of meticulously annotated 4K video captured at 15 fps by four non-overlapping cameras, capturing complex challenges including severe occlusions, nonlinear motion trajectories, and significant viewpoint variations. The dataset encompasses 512 unique vehicle identities and provides standardized baselines and fully reproducible evaluation code for detection, single- and multi-camera tracking, and image-level re-identification. RingTrack bridges the critical gap between academic research and real-world intelligent transportation system deployment, enabling rigorous benchmarking of robust, scalable tracking algorithms in dynamic, infrastructure-constrained traffic environments.

Technology Category

Computer Vision: Motion & TrackingIntelligent Robots: Multimodal Perception & Sensor FusionMachine Learning: Multi-instance/Multi-view Learning

Application Category

Security and Privacy: Tracking, profiling, and countermeasures against themResponsible Web: Machine-in-the-loop, human agency and autonomySystems and Infrastructure for Web, Mobile and WoT: Web applications in cross-disciplinary domains and verticals such as mixed reality, smart cities, and digital health

Abstract

The multi-camera vehicle tracking (MCVT) framework holds significant potential for smart city applications, including anomaly detection, traffic density estimation, and suspect vehicle tracking. However, current publicly available datasets exhibit limitations, such as overly simplistic scenarios, low-resolution footage, and insufficiently diverse conditions, creating a considerable gap between academic research and real-world scenario. To fill this gap, we introduce RoundaboutHD, a comprehensive, high-resolution multi-camera vehicle tracking benchmark dataset specifically designed to represent real-world roundabout scenarios. RoundaboutHD provides a total of 40 minutes of labelled video footage captured by four non-overlapping, high-resolution (4K resolution, 15 fps) cameras. In total, 512 unique vehicle identities are annotated across different camera views, offering rich cross-camera association data. RoundaboutHD offers temporal consistency video footage and enhanced challenges, including increased occlusions and nonlinear movement inside the roundabout. In addition to the full MCVT dataset, several subsets are also available for object detection, single camera tracking, and image-based vehicle re-identification (ReID) tasks. Vehicle model information and camera modelling/ geometry information are also included to support further analysis. We provide baseline results for vehicle detection, single-camera tracking, image-based vehicle re-identification, and multi-camera tracking. The dataset and the evaluation code are publicly available at: https://github.com/siri-rouser/RoundaboutHD.git

Problem

• Lack of realistic multi-camera vehicle tracking datasets
• Need for high-resolution diverse urban scenario data
• Bridge gap between academic research and real-world applications

Innovation

• High-resolution 4K multi-camera dataset
• Real-world roundabout tracking scenarios
• Cross-camera vehicle association data