AI Analysis of Street View Data Reveals Pedestrian and Cyclist Safety Factors

In a study published in the British Medical Journal (BMJ) of Injury Prevention, Dr. Quynh Nguyen, an epidemiologist and statistician at the University of Maryland School of Public Health, employed AI tools to pinpoint crucial environmental factors influencing car-related collisions, as well as accidents involving cyclists and pedestrians.

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.

Dr. Quynh Nguyen, Professor, Epidemiologist and Statistician, School of Public Health, University of Maryland

Nguyen’s work leverages technology and big data sources to address health disparities.

Nguyen and colleagues investigated the connection between automobile accidents and the built environment in the areas where crashes occur. They did this using Google Street View (GSV), an AI tool that provides 360-degree views of streets worldwide. Using virtual mapping, researchers looked at particular road features on a national level, like streetlights and vegetation.

Because we could crunch such a large amount of GSV data from across the country, we got precise results on which built elements influence car crashes. It was clear that places with higher levels of greenery, streetlights, single-lane roads, and sidewalks were associated with fewer fatal car crashes.

Dr. Quynh Nguyen, Professor, Epidemiologist and Statistician, School of Public Health, University of Maryland

The most significant reduction in crashes was observed with sidewalks. Locations with one single-lane road, which are frequently found in rural areas, had 50 % fewer traffic accidents than places with more sidewalks, which had a 70 % reduction.

Street lights and stop signs increased safety for cyclists and pedestrians because they were linked to a decrease in collisions involving these two groups of people. On the other hand, places where there was road construction suffered from an increase in collisions.

Many of the public health issues communities face are often solvable. Emerging technologies and access to extensive data sources have been helpful in finding solutions to some of the public health issues that plague populations.

Xiaohe Yue, Data Analyst and Study Co-Author, School of Public Health, University of Maryland

To provide decision-makers with tried-and-true, workable solutions to increase road safety for motorists, pedestrians, and cyclists, the researchers hope their findings will influence infrastructure and transportation policy.

We hope that our work will lead urban planners and developers to consider the built environment more carefully and so design safer streets and communities,” adds co-author Heran Mane, a Data Analyst working with Yue in SPH.

Nguyen envisions an entirely new avenue of research unfolding.

We are seeing a rise in leveraging data science and AI to enable larger, more efficient, and more timely studies like this one. This research is one demonstration of how we can use AI to improve public health, and we know there’s so much more to come.

Dr. Quynh Nguyen, Professor, Epidemiologist and Statistician, School of Public Health, University of Maryland

Nguyen and colleagues want to expand the types of built environment indicators examined across the United States and explore these features in other countries.

The study was supported by the National Library of Medicine (R01LM012849) and the National Institute on Minority Health and Health Disparities (R01MD015716, R01MD016037).

Journal Reference:

Nguyen, C. Q., et al. (2024) Leveraging computer vision for predicting collision risks: a cross-sectional analysis of 2019–2021 fatal collisions in the USA. Injury Prevention.

Tell Us What You Think

Do you have a review, update or anything you would like to add to this news story?

Leave your feedback
Your comment type

While we only use edited and approved content for Azthena answers, it may on occasions provide incorrect responses. Please confirm any data provided with the related suppliers or authors. We do not provide medical advice, if you search for medical information you must always consult a medical professional before acting on any information provided.

Your questions, but not your email details will be shared with OpenAI and retained for 30 days in accordance with their privacy principles.

Please do not ask questions that use sensitive or confidential information.

Read the full Terms & Conditions.