From Sidewalks to Streetlights, Common Features Shown in Google’s Tech Linked to Crash Frequency
By Sumaya Abdel-Motagaly ’26
Photo by
Stephanie S. Cordle
Most people use Google Street View to help find their way, but University of Maryland researchers employed it in a new study to locate spots where your journey might abruptly end.
In the recent study in the British Medical Journal of Injury Prevention, the research team analyzed the service’s 360-degree views with artificial intelligence tools to identify road-related features linked to collisions involving cars, pedestrians and cyclists.
Then the AI system searched roadways nationwide for such features, correlating it with a census of all fatal motor vehicle collisions from 2019-21, as well as fatal and nonfatal crashes using Washington, D.C., traffic data.
They found sidewalks and streetside greenery correlated to fewer collisions, while roadwork had the opposite effect—an indication of how policymakers can use data to solve public health problems, says Quynh Nguyen, a professor of epidemiology and biostatistics who led the study.
“Car crashes are the leading cause of death for young people between 5 and 29 years old, so it’s crucial to understand how the physical environment can increase or lessen fatal collisions and which communities are most affected by this,” she says.
