Measuring the Built Environment with Google Street View and Machine Learning: Consequences for Crime on Street Segments

The spread of COVID-19 is not evenly distributed. Neighborhood environments may structure risks and resources that produce COVID-19 disparities. Neighborhood built environments that allow greater flow of people into an area or impede social distancing practices may increase residents’ risk for contracting the virus. We leveraged Google Street View (GSV) images and computer vision to detect built environment features (presence of a crosswalk, non-single family home, single-lane roads, dilapidated building and visible wires). We utilized Poisson regression models to determine associations of built environment characteristics with COVID-19 cases. Indicators of mixed land use (non-single family home), walkability (sidewalks), and physical disorder (dilapidated buildings and visible wires) were connected with higher COVID-19 cases. Indicators of lower urban development (single lane roads and green streets) were connected with fewer COVID-19 cases. Percent black and percent with less than a high school education were associated with more COVID-19 cases. Our findings suggest that built environment characteristics can help characterize community-level COVID-19 risk. Sociodemographic disparities also highlight differential COVID-19 risk across groups of people. Computer vision and big data image sources make national studies of built environment effects on COVID-19 risk possible, to inform local area decision-making.

Download Full-text

Using google street view for systematic observation of the built environment: analysis of spatio-temporal instability of imagery dates

International Journal of Health Geographics ◽

10.1186/1476-072x-12-53 ◽

2013 ◽

Vol 12 (1) ◽

pp. 53 ◽

Cited By ~ 48

Author(s):

Jacqueline W Curtis ◽

Andrew Curtis ◽

Jennifer Mapes ◽

Andrea B Szell ◽

Adam Cinderich

Keyword(s):

Built Environment ◽

Systematic Observation ◽

Environment Analysis ◽

Google Street View ◽

Street View ◽

Temporal Instability ◽

Spatio Temporal

Download Full-text

Measuring visual enclosure for street walkability: Using machine learning algorithms and Google Street View imagery

Applied Geography ◽

10.1016/j.apgeog.2016.09.024 ◽

2016 ◽

Vol 76 ◽

pp. 147-153 ◽

Cited By ~ 55

Author(s):

Li Yin ◽

Zhenxin Wang

Keyword(s):

Machine Learning ◽

Learning Algorithms ◽

Machine Learning Algorithms ◽

Google Street View ◽

Street View

Download Full-text

Using Google Street View to examine associations between built environment characteristics and U.S. health outcomes

Preventive Medicine Reports ◽

10.1016/j.pmedr.2019.100859 ◽

2019 ◽

Vol 14 ◽

pp. 100859 ◽

Cited By ~ 6

Author(s):

Quynh C. Nguyen ◽

Sahil Khanna ◽

Pallavi Dwivedi ◽

Dina Huang ◽

Yuru Huang ◽

...

Keyword(s):

Built Environment ◽

Health Outcomes ◽

Google Street View ◽

Street View

Download Full-text

Google Street View Derived Built Environment Indicators and Associations with State-Level Obesity, Physical Activity, and Chronic Disease Mortality in the United States

International Journal of Environmental Research and Public Health ◽

10.3390/ijerph17103659 ◽

2020 ◽

Vol 17 (10) ◽

pp. 3659

Author(s):

Lynn Phan ◽

Weijun Yu ◽

Jessica M. Keralis ◽

Krishay Mukhija ◽

Pallavi Dwivedi ◽

...

Keyword(s):

Physical Activity ◽

Built Environment ◽

Health Outcomes ◽

State Level ◽

Premature Mortality ◽

The United States ◽

Single Family ◽

Google Street View ◽

Street View ◽

Neighborhood Built Environment

Previous studies have demonstrated that there is a high possibility that the presence of certain built environment characteristics can influence health outcomes, especially those related to obesity and physical activity. We examined the associations between select neighborhood built environment indicators (crosswalks, non-single family home buildings, single-lane roads, and visible wires), and health outcomes, including obesity, diabetes, cardiovascular disease, and premature mortality, at the state level. We utilized 31,247,167 images collected from Google Street View to create indicators for neighborhood built environment characteristics using deep learning techniques. Adjusted linear regression models were used to estimate the associations between aggregated built environment indicators and state-level health outcomes. Our results indicated that the presence of a crosswalk was associated with reductions in obesity and premature mortality. Visible wires were associated with increased obesity, decreased physical activity, and increases in premature mortality, diabetes mortality, and cardiovascular mortality (however, these results were not significant). Non-single family homes were associated with decreased diabetes and premature mortality, as well as increased physical activity and park and recreational access. Single-lane roads were associated with increased obesity and decreased park access. The findings of our study demonstrated that built environment features may be associated with a variety of adverse health outcomes.

Download Full-text

Using Google Street View to Audit the Built Environment: Inter-rater Reliability Results

Annals of Behavioral Medicine ◽

10.1007/s12160-012-9419-9 ◽

2012 ◽

Vol 45 (S1) ◽

pp. 108-112 ◽

Cited By ~ 89

Author(s):

Cheryl M. Kelly ◽

Jeffrey S. Wilson ◽

Elizabeth A. Baker ◽

Douglas K. Miller ◽

Mario Schootman

Keyword(s):

Built Environment ◽

Rater Reliability ◽

Google Street View ◽

Street View

Download Full-text

Health and the built environment in United States cities: measuring associations using Google Street View-derived indicators of the built environment

BMC Public Health ◽

10.1186/s12889-020-8300-1 ◽

2020 ◽

Vol 20 (1) ◽

Cited By ~ 4

Author(s):

Jessica M. Keralis ◽

Mehran Javanmardi ◽

Sahil Khanna ◽

Pallavi Dwivedi ◽

Dina Huang ◽

...

Keyword(s):

United States ◽

Built Environment ◽

Google Street View ◽

Street View

Download Full-text

Using deep learning to examine the correlation between transportation planning and perceived safety of the built environment

Environment and Planning B Urban Analytics and City Science ◽

10.1177/2399808320959079 ◽

2020 ◽

pp. 239980832095907

Author(s):

Justin B Hollander ◽

Giorgi Nikolaishvili ◽

Alphonsus A Adu-Bredu ◽

Minyu Situ ◽

Shabnam Bista

Keyword(s):

Neural Network ◽

Built Environment ◽

Transportation Planning ◽

Regression Models ◽

Large Set ◽

Perceived Safety ◽

Google Street View ◽

Street View ◽

Safety Perception ◽

Transportation Policies

In this study, we attempt to estimate the effects of various transportation policies on the perceived safety of the built environment. We train a convolutional neural network on a dataset of safety perception scores for Google Street View images taken in Boston, MA . We then apply the trained neural network to a large set of Google Street View images of coordinates in Montreal and Toronto to generate their respective safety perception scores. We estimate probit, logit, and ordinary least squares regression models using our cross-sectional dataset consisting of safety perception scores, as well as transportation policy variables and a set of control variables, by regressing the safety perception scores on the remaining set of variables. We answer our research question by observing the direction, magnitude, and statistical significance of the coefficient estimates associated with the policy variables across all regression models. We studied and cataloged transportation policies planned for over the past 10 years in both cities. We found that those census tracts with the poorest safety scores were the same places where planners focused their transportation investments. The study makes an important contribution to transportation planning methodologies by drawing on the novel data source of Google Street View images, to understand the safety of an area.

Download Full-text