Researchers from the University of Chicago and the MRC Epidemiology Unit at the University of Cambridge have released a report describing how Google Street View has the potential to estimate the frequency and distribution of travel patterns, including cycling, in cities.

The study, published in PLOS ONE, describes the analysis of 2,000 Google Street View images from 1,000 random locations in 34 randomly selected UK cities. The researchers counted the number of pedestrians, parked cars, cyclists, motorcycles, cars, buses, vans and trucks in each image to build up an overview of each area’s travel preferences.

“Establishing a good relationship between Google Street View data and population-level surveys is highly encouraging,” said Dr Rahul Goel of the MRC Epidemiology Unit and lead author of the paper. “We are excited about the global applications of this study, especially in settings where availability of data on walking and cycling levels has been traditionally scarce”.

The scientists compared the Street View data to frequency of travel modes as reported in the 2011 Census, and walking data from 2010 to 2012 in the Active People Survey, an annual survey of physical activity in England. Street View data from 2010 to 2012 was used so all collected data covered roughly the same period.

Covid-19 Report — Updated twice a week Understanding the Covid-19 outbreak, the economic impact and implications for specific sectors

Covid-19 executive briefing report cover
GlobalData

Our parent business intelligence company

The results demonstrated a strong correlation between the Street View observations and levels of bicycle, public transport and motorbike use as reported by the Census and Active People Survey, and a moderate correlation for walking.

Researchers were also able to conduct a pilot analysis on predicting the gender distribution of cyclists, which is said to have yielded ‘positive’ results. Google’s service is already widely to inform decisions on road infrastructure and green cover; the observations made by the universities suggest that Street View could also be used to influence decisions involving humans and their behaviour.

“If something is not measured then it is often ignored,” said Dr James Woodcock of the MRC Epidemiology Unit, principal investigator of the study and senior author of the paper. “It is surprising how little we know about how much cycling there is in many cities around the world. Google Street View has great potential for understanding how people travel in many countries.

“The data is freely available and is collected in a more consistent way than many traditional surveys”.