MIT researchers have developed an algorithm that can predict whether a car is about to run a red light, a calculation they estimate could prevent millions of crashes and 700 deaths each year if paired with vehicle-to-vehicle (V2V) communication.
Using data collected from DOT-sponsored surveillance of a busy intersection in Christianburg, Virginia, to track vehicle speed and location, the researchers could determine, within two seconds of a car approaching an intersection, with 85 percent accuracy whether it would run a red light. via Wired
Photo: Flickr/midweekpost
