What if we could use technology to predict where vehicle collisions involving people who walk or bike will occur, then take steps to prevent them? Would you want to help? Well, now you can.
Volunteers are needed to help train computers to recognize objects and flag “near misses” at intersections. An example of a near-miss is when a driver nearly hits someone in a crosswalk.
Here’s how it works: your task is to view a short clip of a pre-recorded traffic scene, then label and track the movement of each person or vehicle within the screen. By doing so, the computer can begin to distinguish a person walking, biking, or using a wheelchair; a bus or car; then recognize patterns to identify near misses. Using the data from the video analytics, engineers could then take corrective actions to prevent future crashes.
|Technology like heat mapping has the potential to help us improve road safety.|
Fair warning to potential volunteers – until you get accustomed to using the labeling tools, it may take you several minutes to complete the task – plan on at least five minutes or longer per task at the start. Once you master the image tracking tools, your speed will likely increase. You can submit just one task, or complete as many as you’d like.
This work is part of a multi-city, multi-organizational partnership called Video Analytics Toward Vision Zero, a strategy to eliminate all traffic fatalities and serious injuries while increasing safety for all users of the roadway.
|We need the public’s help to use our crowd-sourcing tool to analyze video and teach computers how to tell the difference between cars, buses, bikes and pedestrians.|
Vehicle crashes involving pedestrians and bicyclists are on the rise in Washington state, as well as in other states. Fatal collisions involving bicyclists and pedestrians in Washington increased 6 percent from 100 in 2015 to 106 in 2016.
Why not give it a try? With your help, researchers can create a database that one day may save a life and make our roadways safer for everyone.