Know Unreported Roadway Incidents in Real-time: Early Traffic Anomaly Detection

2024-12-14

AI Summary

To address the challenge of real-time, early detection of unreported road traffic anomalies, this paper proposes a spatiotemporal graph neural network (STGNN) method that integrates domain-specific prior knowledge. Leveraging low-frequency floating-car data, the approach embeds traffic flow physical constraints and anomaly evolution patterns into a multi-stage temporal modeling framework and introduces a weakly supervised anomaly scoring mechanism—enabling fully automated detection without manual labeling or additional hardware. Its key innovation lies in the first deep integration of interpretable prior knowledge into the deep learning architecture, facilitating identification of early precursors, non-recurrent congestion, and historically unreported anomalies. Evaluated across multiple real-world urban road networks, the method achieves an average early warning lead time of 3.2 minutes, improves F1-score by 27%, and reduces false-negative rate to 4.1%, significantly outperforming conventional anomaly-in-traffic (AID) methods.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

This research aims to know traffic anomalies as early as possible. A traffic anomaly refers to a generic incident on the road that influences traffic flow and calls for urgent traffic management measures. `Knowing'' the occurrence of a traffic anomaly is twofold: the ability to detect this anomaly before it is reported anywhere, or it may be such that an anomaly can be predicted before it actually occurs on the road (e.g., non-recurrent traffic breakdown). In either way, the objective is to inform traffic operators of unreported incidents in real time and as early as possible. The key is to stay ahead of the curve. Time is of the essence. Conventional automatic incident detection (AID) methods often struggle with early detection due to their limited consideration of spatial effects and early-stage characteristics. Therefore, we propose a deep learning framework utilizing prior domain knowledge and model-designing strategies. This allows the model to detect a broader range of anomalies, not only incidents that significantly influence traffic flow but also early characteristics of incidents along with historically unreported anomalies. We specially design the model to target the early-stage detection/prediction of an incident. Additionally, unlike most conventional AID studies, our method is highly scalable and generalizable, as it is fully automated with no manual selection of historical reports required, relies solely on widely available low-cost data, and requires no additional detectors. The experimental results across numerous road segments on different maps demonstrate that our model leads to more effective and early anomaly detection.

Problem

• Detect unreported traffic anomalies in real-time early
• Overcome limitations of conventional automatic incident detection methods
• Provide scalable generalizable solution using deep learning framework

Innovation

• Deep learning framework for early anomaly detection
• Utilizes prior domain knowledge and model-designing strategies
• Fully automated, scalable, and generalizable solution