Next City reports on something that proves that everything old becomes new again with innovation, including the use of cameras monitoring intersections. UBC engineering professor Tarek Sayed states what everyone who has looked at the civic systems to get speed bumps or signalized crosswalks knows-“We have to wait for collisions to happen before we can do anything. A fundamental ethical and practical problem which faces traffic engineers is, in order to improve safety, you need a certain number of collisions … which you would try to prevent later,” says the University of British Columbia civil engineering professor. “It’s very reactive.”
Sayed has taken a proactive approach, developing a video camera system that monitors intersections for near collision misses, and has computers track the results. “The system, called, somewhat inelegantly, “computer vision and automated safety analysis,” uses off-the-shelf cameras, or cameras that are already installed in an area, to film a given intersection. Computer algorithms can track anything that moves through the intersection — cars, bikes, people — and can figure out quite a bit about each one. The computer knows whether the moving blip is a person or a car, how fast they’re going, how close they got to hitting another road user. The computer can even tell, with about 80 percent accuracy, whether a person is distracted by their phone while walking.”
Driver distraction is measured by how long it takes the driver to stop the car. Sayed also suggests that lower vehicular speeds would lessen the impact of any pedestrian crashes. This system is used in several countries and the redesign of one intersection in Edmonton Alberta had a 92 per cent reduction in collisions after the computer vision and safety analysis.
This system was used in the analysis and design for the upgrade to the Burrard/Pacific intersection. Can’t wait to see the final result.
Also interested to see the before vs after design … what designers thought worked vs what it suggested would.
Author
Reblogged this on Sandy James Planner.
Very interesting…
This is, in essence, the same sort of thing as self-driving car technology. The difference is how the data is applied – cool!
I’ll just suggest that it would be an interesting exercise to design and implement an intersection that begins by providing the best possible options to pedestrians, then cyclists, with automobile accommodation left to squeeze into the remaining space and budget.