FLUID: A Fine-Grained Lightweight Urban Signalized-Intersection Dataset of Dense Conflict Trajectories

2025-08-30

AI Summary

Existing trajectory datasets for traffic participants suffer from insufficient scene coverage, limited semantic information, and inadequate spatial-temporal accuracy—particularly in urban signalized intersections—and critically lack fine-grained representations of high-density conflict trajectories. To address this, we propose a lightweight end-to-end UAV-based trajectory processing framework integrating aerial video acquisition, high-precision trajectory extraction, traffic signal phase synchronization, georeferencing, and multi-level conflict classification. Leveraging this framework, we construct the first multimodal trajectory dataset specifically designed for dense-conflict urban signalized intersections. The dataset encompasses three representative intersection types, 20,000+ trajectories across eight participant categories, and 5 hours of raw video footage, with an average conflict frequency of 2 per minute and 25% of motor vehicles involved in conflicts. Validation against DataFromSky and ground-truth field measurements confirms reliable localization and event annotation accuracy. This work substantially advances data support for modeling complex traffic interactions and developing robust autonomous driving decision-making systems.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Multi-modal Vision
• Application Domains: Mobility, Driving & Flight

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Security and Privacy: Data transparency and provenance
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data

Abstract

The trajectory data of traffic participants (TPs) is a fundamental resource for evaluating traffic conditions and optimizing policies, especially at urban intersections. Although data acquisition using drones is efficient, existing datasets still have limitations in scene representativeness, information richness, and data fidelity. This study introduces FLUID, comprising a fine-grained trajectory dataset that captures dense conflicts at typical urban signalized intersections, and a lightweight, full-pipeline framework for drone-based trajectory processing. FLUID covers three distinct intersection types, with approximately 5 hours of recording time and featuring over 20,000 TPs across 8 categories. Notably, the dataset averages two vehicle conflicts per minute, involving roughly 25% of all motor vehicles. FLUID provides comprehensive data, including trajectories, traffic signals, maps, and raw videos. Comparison with the DataFromSky platform and ground-truth measurements validates its high spatio-temporal accuracy. Through a detailed classification of motor vehicle conflicts and violations, FLUID reveals a diversity of interactive behaviors, demonstrating its value for human preference mining, traffic behavior modeling, and autonomous driving research.

Problem

• Addresses limitations in urban intersection traffic datasets
• Provides fine-grained trajectory data for dense conflict analysis
• Enables traffic behavior modeling and autonomous driving research

Innovation

• Drone-based fine-grained trajectory dataset
• Lightweight full-pipeline processing framework
• Multi-category traffic participant conflict analysis