As cities worldwide seek effective strategies to address rising traffic fatalities, a new study published in Management Science reveals AI-powered traffic cameras offer a breakthrough solution—not only catching violations, but meaningfully improving overall road safety.
“Our study shows that AI-powered traffic cameras don’t just document violations—they promote safer driving behavior and significantly reduce accidents, even in nearby areas without cameras,” says Zhi (Aaron) Cheng, at the London School of Economics.
The study, “Automated Enforcement and Traffic Safety,” conducted by Cheng, alongside researchers from Sun Yat-sen University, and the University of Wisconsin–Madison, finds that advanced cameras using artificial intelligence and continuous video recording can reduce traffic accidents far more effectively than conventional enforcement systems.
Analyzing data from a major metropolitan city in China, the researchers estimated that citywide deployment of AI-enabled cameras could have prevented approximately 1,190 accidents, 496 injuries or fatalities, and nearly $1 million in property losses per year. Importantly, the study found that the safety improvements did not merely shift accidents to nearby intersections—a common concern with older traffic enforcement technologies.
Three main factors explain the success of AI-powered enforcement:
- Smarter detection of a broader range of unsafe driving behaviors.
- Real-time video recording that supports more accurate accident investigations.
- Behavioral deterrence, encouraging drivers to adopt safer habits even outside monitored zones.
“Traffic safety is a persistent and complex challenge,” says Min-Seok Pang at the University of Wisconsin–Madison. “Our findings offer evidence that carefully deployed AI technologies can create real, system-wide improvements without unintended negative consequences.”
With U.S. traffic fatalities remaining stubbornly high in recent years, the study offers timely insights for policymakers, transportation agencies and urban planners seeking data-driven, AI-powered solutions to save lives and improve public safety.
More information:
Zhi (Aaron) Cheng et al, Automated Enforcement and Traffic Safety, Management Science (2025). DOI: 10.1287/mnsc.2023.00575
Institute for Operations Research and the Management Sciences
Citation:
AI traffic enforcement minimizes crashes without shifting risk, study finds (2025, May 20)
retrieved 20 May 2025
from https://techxplore.com/news/2025-05-ai-traffic-minimizes-shifting.html
This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no
part may be reproduced without the written permission. The content is provided for information purposes only.
