Research To Improve Detection of Snowy and Icy Roadways Will Improve Safety

Posted: Jun 13, 2025

Researchers at the University of Utah have developed technology that can potentially conduct multi-lane roadway ice/snow coverage estimation, which is superior to the state-of-the-art single-spot measurements. The technology, which combines non-contact dual-spectrum cameras, computer vision, and machine learning algorithms, promises to improve road safety and transportation in adverse weather conditions by improving snow and ice detection so that road agencies can respond more rapidly and effectively to deteriorating road conditions. There is potential for these systems to be integrated into existing intelligent transportation systems, thereby augmenting winter roadway safety.

Xuan Zhu, Ph.D.
University of Utah

Winter Safety Improvement with Computer Vision and Transfer Learning
MPC-24-572