Estimating City-Scale Pedestrian Movement With Sensor Networks for Count Data

Abstract

Walking remains an integral part of modern transportation and therefore pedestrian behaviour influences the functioning, management, and further design of intelligent transportation systems. The recent widespread deployment of sensors that collect anonymous pedestrian counts in city locations presents an opportunity. Data on pedestrian dynamics are now recorded on a scale beyond the commonly studied individual level while preserving information on how pedestrians utilize transportation facilities, such as roads and pathways. However, it remains unclear how the pedestrian dynamics on a city scale can be recovered from such aggregated measurements. Here, we integrate information captured by sensor networks to estimate city-scale pedestrian movement represented by flows between locations with sensors. We propose an estimator based on the maximum entropy principle that uses only information collected by the sensing system. Notably, the estimation problem is inherently underdetermined, as the observations are insufficient relative to the complexity of city-scale pedestrian movement. We address this by examining the ensemble average of feasible systems under the observation, which gradually yields an exact representation of the system as it becomes determined, such as for high sensor densities. In a case study, we apply our estimator to three real-world datasets, assuming stronger interactions between counts recorded by nearby sensors. The estimator recovers stable, time-dependent, and spatially heterogeneous pedestrian flows between sensor locations. The proposed framework, leveraging emerging sensor data, opens new possibilities for accounting for pedestrian dynamics in intelligent transportation systems.