From Data to Decisions: Understanding Pedestrian Flow with WiFi Scanner Data

Abstract
Understanding pedestrian movement is crucial for designing walkable and accessible urban environments. Traditional data collection methods, such as manual counts and surveys, often provide limited spatial and temporal coverage, Leading to an incomplete representation of pedestrian activity. This study examines WiFi scanner data as a scalable and automated alternative for analysing pedestrian flow in urban areas.
WiFi scanners detect anonymised signals from mobile devices, providing a privacy-conscious method for estimating pedestrian presence. This study validates WiFi-derived data against manual counts to assess its accuracy and reliability. Additionally, integrating this data with urban and environmental factors through geospatial analysis generates detailed pedestrian flow maps, capturing variations in movement patterns over time and across different locations.
The findings demonstrate that WiFi scanner data effectively represents pedestrian activity by distinguishing between peak and off-peak periods and identifying areas of high and low foot traffic. This approach provides continuous, detailed insights that support data-driven urban planning. These results can help policymakers enhance pedestrian infrastructure, improve accessibility, and create more inclusive urban spaces.
Keywords: Urban Mobility, Pedestrian Flow, WiFi Sensing, Spatial Analysis, Smart Cities.