Key Factors Affecting the Accuracy of Reidentification of Trucks over Long Distances Based on Axle Measurement Data

Abstract

Vehicle reidentification methods can be used to anonymously match vehicles crossing two locations based on vehicle attribute data. This paper investigates key factors that affect the accuracy of vehicle reidentification algorithms. The analyses are performed with reidentification algorithms to match commercial vehicles that cross upstream and downstream pairs of weigh-in-motion (WIM) sites that are separated by long distances, ranging from 70 to 214 mi. The data to support this research come from 17 fixed WIM sites in Oregon. Data from 14 pairs of WIM sites are used to evaluate how various factors affect matching accuracy; factors include the distance between two sites, travel time variability, truck volumes, and sensor accuracy or consistency of measurements. After the vehicle reidentification algorithm is run for each of these 14 pairs of sites, the matching error rates are reported. The results from the testing data sets show a large variation in terms of accuracy. Sensor accuracy and volumes have the greatest impacts on matching accuracy; distance alone does not have a significant effect.