Estimating city-level travel patterns using street imagery: A case study of using Google Street View in Britain.

Rahul Goel,Rob Johnson,Manoradhan Murugesan,Soren Brage,Leandro M T Garcia,James Woodcock,Kavi Bhalla,Rachel Aldred,Anna Goodman,Manoj Srinivasan

doi:10.1371/journal.pone.0196521

Abstract

BackgroundStreet imagery is a promising and growing big data source providing current and historical images in more than 100 countries. Studies have reported using this data to audit road infrastructure and other built environment features. Here we explore a novel application, using Google Street View (GSV) to predict travel patterns at the city level.MethodsWe sampled 34 cities in Great Britain. In each city, we accessed 2000 GSV images from 1000 random locations. We selected archived images from time periods overlapping with the 2011 Census and the 2011–2013 Active People Survey (APS). We manually annotated the images into seven categories of road users. We developed regression models with the counts of images of road users as predictors. The outcomes included Census-reported commute shares of four modes (combined walking plus public transport, cycling, motorcycle, and car), as well as APS-reported past-month participation in walking and cycling.ResultsWe found high correlations between GSV counts of cyclists (‘GSV-cyclists’) and cycle commute mode share (r = 0.92)/past-month cycling (r = 0.90). Likewise, GSV-pedestrians was moderately correlated with past-month walking for transport (r = 0.46), GSV-motorcycles was moderately correlated with commute share of motorcycles (r = 0.44), and GSV-buses was highly correlated with commute share of walking plus public transport (r = 0.81). GSV-car was not correlated with car commute mode share (r = –0.12). However, in multivariable regression models, all outcomes were predicted well, except past-month walking. The prediction performance was measured using cross-validation analyses. GSV-buses and GSV-cyclists are the strongest predictors for most outcomes.ConclusionsGSV images are a promising new big data source to predict urban mobility patterns. Predictive power was the greatest for those modes that varied the most (cycle and bus). With its ability to identify mode of travel and capture street activity often excluded in routinely carried out surveys, GSV has the potential to be complementary to new and traditional data. With half the world’s population covered by street imagery, and with up to 10 years historical data available in GSV, further testing across multiple settings is warranted both for cross-sectional and longitudinal assessments.

Highlights

Urban mobility data is crucial to understand travel patterns, to plan and evaluate policies and interventions, and to analyse their social, health and environmental impacts [1, 2]
Google Street View (GSV)-pedestrians was moderately correlated with past-month walking for transport (r = 0.46), GSV-motorcycles was moderately correlated with commute share of motorcycles (r = 0.44), and GSV-buses was highly correlated with commute share of walking plus public transport (r = 0.81)
With its ability to identify mode of travel and capture street activity often excluded in routinely carried out surveys, GSV has the potential to be complementary to new and traditional data

Summary

Introduction

Urban mobility data is crucial to understand travel patterns, to plan and evaluate policies and interventions, and to analyse their social, health and environmental impacts [1, 2]. Household travel surveys provide good data on personal travel patterns, but they are resourceintensive, often available only at the national or regional level, conducted infrequently, and aimed at long-term transport planning and not at surveillance. Cycle or pedestrian counts– by human observers or sensors–are more common, but usually cover specific areas or junctions within cities and lack representativeness and are difficult to compare across cities. In this context, it is imperative to develop innovative, comparable, and cost-effective approaches to estimate walking, cycling and other travel patterns in cities. We explore a novel application, using Google Street View (GSV) to predict travel patterns at the city level

Objectives

Methods

Results

Discussion

Conclusion