Lightweight Occupancy Estimation on Freeways Using Extended Floating Car Data

Abstract

Advanced traffic management systems rely heavily on technology to perform accurate estimations of the current state of the traffic as well as its short-term evolution. The objectives are improving traffic flow and enhancing road safety. Their success is based on accurate monitoring of two key variables, specifically speed and occupancy. The latter of the two has, to date, received significantly less attention from the scientific community. In this work we present a lightweight method to perform “on-line” occupancy estimation. We first propose three occupancy measurements calculated from data collected by a floating car: vehicle count, percentage of stop time, and headway. We then extend these discrete values to a continuous estimation of occupancy in space and time. The proposed estimators are based on a pairwise linear regression of each of the previously calculated measurements over certain references obtained from other floating cars or magnetic loop detectors. The method has been calibrated and validated under real traffic conditions and data. Despite the ease of implementation, the method is able to reproduce the occupancy values generated by the actual loop detectors, achieving promising results, with estimation errors down to 6.52%, even before multivehicle systems are considered.