Abstract-This paper proposes a novel anomaly classification algorithm that can be deployed in a distributed manner and utilizes microscopic traffic variables shared by neighbouring vehicles to detect and classify traffic anomalies under different traffic conditions. The algorithm which incorporates multi-resolution concepts is based on the likelihood estimation of a neural network output and a bisection-based decision threshold. We show that when applied to real-world traffic scenarios, the proposed algorithm can detect all the traffic anomalies of the reference test data set; this represents a significant improvement over our previously proposed algorithm [1]. We also show that the proposed algorithm can effectively detect and classify traffic anomalies even when i) the microscopic traffic variables are available from only a fraction of the vehicle population and ii) some microscopic traffic variables are lost due to degradation in V2V and/or V2I communications.

No abstract

No abstract

No abstract

This paper proposes a novel inference method to estimate lane-level traffic flow, time occupancy and vehicle inter-arrival time on road segments where local information could not be measured and assessed directly. The main contributions of the proposed method are 1) the ability to perform lane-level estimations of traffic flow, time occupancy and vehicle inter-arrival time and 2) the ability to adapt to different traffic regimes by assessing only microscopic traffic variables. We propose a modified Kriging estimation model which explicitly takes into account both spatial and temporal variability. Performance evaluations are conducted using real-world data under different traffic regimes and it is shown that the proposed method outperforms a Kalman filter-based approach.