Occupancy Estimation using WiFi: A Case Study for Counting Passengers on Busses

Abstract

Occupancy estimation in public busses is growing in importance due to its usefulness in planning public transport systems effectively. Bus occupancy data can be used in real time by transport companies to better estimate demand, improve customer satisfaction while also enabling long-term analyses for the purpose of route optimisation. Additionally, in scenarios where busses are used to replace other modes of public transport, such as metropolitan trains during schedule/unscheduled stoppages, occupancy estimation can help operators determine the deployment requirements of replacement busses. In this paper, we present a low cost WiFi-based system for occupancy estimation in busses. In particular, we propose a novel algorithm for occupancy estimation that reduces the problem of overestimation encountered in WiFi-based occupancy estimation approaches. We validate the accuracy and efficiency of the proposed algorithm and the WiFi-based occupancy estimation solution via a real-world experiment.