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

TL;DR

This paper presents a deep learning framework for real-time early detection of unreported traffic anomalies, improving traffic management by predicting incidents before they are reported or occur.

Contribution

It introduces a scalable, fully automated deep learning model that leverages domain knowledge to detect a wide range of traffic anomalies early, without manual report selection or additional sensors.

Findings

More effective early anomaly detection across diverse road segments

Model predicts incidents before they are reported or occur

No need for manual data labeling or extra detectors

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.