Know Unreported Roadway Incidents in Real-time: Early Traffic Anomaly Detection
Haocheng Duan, Hao Wu, Sean Qian
TL;DR
The paper tackles the challenge of knowing road anomalies in real time, including unreported incidents, by framing early anomaly detection as a multi-step, graph-aware prediction problem. It introduces a sub-graph per link model, denoising of anomaly labels via slowdown-speed priors, ahead-labeling to capture early-stage signals, and a multi-step Seq2Seq/Transformer-based predictor with threshold adaptation. By training on anomaly-labeled data derived from both incident reports and domain knowledge, the approach improves timeliness, achieving alerts 5–42 minutes before traditional reports on ten segments across two regions, while maintaining acceptable false-alarm rates. The work demonstrates scalability, generalizability with low-cost, widely available data, and practical applicability for proactive incident management and traffic control.
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.