Introducing Video Analytics Towards Vision Zero: A new way to prevent collisions before they happen

When the Vision Zero LA team comes to work every day, we know the statistics about traffic collisions. In addition to the national numbers (40,000 deaths and 4.6 million injuries), we think locally: Every year more than 200 people die on the streets of Los Angeles, half of whom are pedestrians or cyclists. Traffic collisions are the leading cause of death for children between the ages of 2 and 14.

Crowdsourced technology has already changed the way many of us get around (Lyft, Uber, Waze, and so on). What if we could also use technology to predict where vehicle collisions involving pedestrians and bicyclists will occur, and then take steps to prevent them? Thanks to a new online platform and partnership called Video Analytics Towards Vision Zero, everyday citizens can play a role in teaching computers how to recognize and prevent potential traffic collisions before they happen.

By using footage from traffic cameras across North America, VAVZ will “teach” computers how to recognize near-miss collisions. Data from these machine learning systems will allow transportation engineers to predict where crashes will occur and take proactive measures to prevent them.

To help this platform reach its potential, volunteers are needed starting June 1.! Here’s how it works: You will 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 of near misses. 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 — but once you master the image tracking tools, your speed will increase. You can submit just one task, or complete as many as you’d like.

If you’d like more information, you can visit the VAVZ website and see more of their research (including an article in ITE Journal).

For additional information on this partnership please contact Franz Loewenherz, project manager of the Video Analytics Towards Vision Zero Partnership, at +1-425-452-4077 or floewenherz@bellevuewa.gov.