Quantifying the vibrancy of streets: Large-scale pedestrian density estimation with dashcam data

This paper proposes a new methodology for measuring street-level pedestrian density that combines the strengths of image-based observations with the scalability of drive-by sensing. Despite its importance, existing methods for measuring pedestrian activity have several limitations, including high costs, limited coverage, and privacy concerns. To overcome these issues, our approach exploits operation logs generated by dashboard cameras of moving vehicles to estimate pedestrian density for each street, which is validated with data from approximately 3,000 taxis operating in central Tokyo. We produce vibrancy maps for 292 station areas in central Tokyo by leveraging machine learning to estimate pedestrian density in streets where measurement data is scarce. We also evaluate the reliability and coverage of the measurement and illustrate how the measured pedestrian density data can be utilized for assessing the validity of walkability measures. The paper concludes that this approach could provide valuable data to inform urban planning and city operations. • We proposed and validated a new methodology to measure pedestrian density at street scale from operation logs generated by dashboard cameras of moving vehicles. • By analyzing dashcam data from around 3,000 taxis in central Tokyo, we captured pedestrian activity for over 50% of the area’s time and space. • We explored a machine learning approach to estimate pedestrian density in data-scarce streets, enabling comparisons across different neighborhoods. • We found a strong correlation between street pedestrian density and walkability measures, particularly with the number of nearby amenities.