Safety Management

Using computer vision to detect pedestrian, bicycle, and vehicle near-misses and high risk events

Using computer vision, video cameras, and AI to detect, count, measure speed, and intent on pedestrian, bicycle, and vehicles at intersections, crosswalks, multimodal lanes and other higher-risk sites. We are using edge computing, computer vision, and deep learning neural networks to automatically detect presence, count, and measure speed of pedestrians, cyclists, and vehicles to inform traffic signaling systems and digital signage about potential traffic safety risks. Cities can also use the solution for touchless crosswalks and to protect pedestrians and cyclists as they approach parking garages in cities.

Idea Submitted by Roger Brook, Boulder AI

List your Agency /Division / Bureau, County, City Univ. or Other Boulder AI

Why is this a priority and what are the benefits for the State/County/City?

This idea is aligned with Vision Zero and traffic safety goals ... as well as public health goals (e.g. touchless cross walks). The technology can be used in urban, suburban, and highway scenarios. Data is generated so transportation engineers can remotely monitor traffic risk scenarios for both planning and real time operational purposes.

Voting

5 votes
Ideate
Idea No. 201