Developing a Computer Vision-based Decision Support System for Intersection Safety Monitoring and Assessment of Vulnerable Road Users

Over the last decade and according to NHTSA’s safety reports, the annual average number of pedestrian and bicyclist roadway fatalities in US has been around 4,600 and 700, respectively; the annual average number of pedestrian and bicyclist injuries has hovered around 65,000 and 50,000, respectively. Between 2009 and 2016, the number of pedestrian and bicyclist fatalities saw a marked trend upward. Taken together, the overall percentage of pedestrian and bicycle crashes now accounts for 17% of total fatalities, up from 13% only a decade ago. This alarming trend urgently needs attention by researchers and practitioners. The proposed project aims to make use of advanced computer vision techniques to proactively conduct safety assessment at intersections for bicycling and walking by applying safety surrogate measures. We will develop a decision support system that can be used to identify high pedestrian and bicycle crash risk locations and measure safety effects of countermeasures.

Principal Investigator: 

Arash Jahangiri, Ph.D.

PI Contact Information:
San Diego State University

Project Number: