UTFP-AD: Urban Traffic Flow Pattern Anomaly Detection Using Spatiotemporal Data

Detecting urban anomalies helps city managers solve traffic problems in a timely manner, prevent safety hazards, and make more scientific and rational urban development plans. However, most existing urban anomaly detection methods focus on single time slots and overlook the impact of anomalous events on traffic flow patterns. To this end, we propose a novel urban traffic flow pattern anomaly detection method in this paper, referred to as UTFP-AD. Our approach constructs traffic flow over a period of time as a temporal probability distribution and uses traffic flow dynamics to detect anomalous patterns. Specifically, we construct temporal probability distributions to represent regional traffic flow patterns and calculate the traffic flow dynamics to reflect traffic flow changes. Independent and correlated feature vectors are then input into the proposed Multi-One-Class Support Vector Machine to identify the final anomalous regions. For validation, we conducted experiments using both synthetic and real-world data, comparing our method with six existing methods. The experimental results demonstrate that UTFP-AD significantly outperforms the existing methods in terms of Recall, F1Score and hit rate.