Anomaly Detection using Microscopic Traffic Variables on Freeway Segments

Abstract

This paper proposes and assesses the effectiveness of monitoring vehicular traffic anomalies using microscopic traffic variables, namely relative speed and inter-vehicle spacing. We present an algorithm that detects transient changes in traffic patterns using microscopic traffic variables. In particular, we show that when applied to real-world scenarios, our algorithm can use the variance of statistics of relative speed to detect traffic anomalies and precursors to non-recurring traffic congestion. The performance of the proposed algorithm is also assessed using a microscopic traffic simulation environment, where we show that with minimum prior knowledge, the proposed algorithm has comparable performance to an ideally placed loop detector monitoring the standard deviation of speed. The algorithm also performs very well even when the microscopic traffic variables are available only from a fraction of the complete population of vehicles.