Video analytics help train computers to recognize road users, prevent collisions
In 2016, road crashes resulted in 40,000 deaths and 4.6 million injuries in the United States. For young people under age 19, these collisions were the leading cause of death.
What if we could use technology to predict where vehicle collisions involving pedestrians and bicyclists will occur, then take steps to prevent them? Would you want to help? Well, now you can.
Portland State University is particpating in a multi-city, multi-organizational partnership called Video Analytics Towards Vision Zero. As indicated in this ITE Journal Article, this technology development partnership aims to use footage from traffic cameras across North America to “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.
The partnership invites public participation in the next project milestone – using crowdsourcing to analyze video and teach computers to identify a person in a wheelchair, on a bike or in a car, as well as patterns of movement in intersections. The more volunteers who take part, the better computers will learn to recognize near-miss collisions.
To participate, visit: http://www.ite.org/visionzero/videoanalytics/.
Here’s how it works: volunteers 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. 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 increase. You can submit just one task, or complete as many as you’d like. Volunteers are needed starting June 1.
For additional information on this partnership please contact Franz Loewenherz, project manager of the Video Analytics Towards Vision Zero Partnership.