Viva, the transport technology scaleup transforming cities into smarter and more efficient places to live and work, has today announced the launch of ‘Near Miss’ in the US. Near Miss uses the power of Computer Vision to anonymously and accurately track the path of road users to generate statistics on Near Misses and helps users identify their root causes. By combining speed, footprint and trajectory datasets to identify dangerous interactions, Near Miss data reveals the most hazardous areas of road space and informs proactive safety interventions. Viva is able to provide unprecedented levels of accuracy and reliability by harnessing real-time continuous data in an area where it hadn’t previously existed.
The process of making road safety improvements is often a reactive one, with limited contextual information. Viva’s Near Miss gives cities the ability to predict where accidents are likely to occur next, identifying the most probable causes of accidents so that interventions can be actioned early and serious injury can be prevented.
Viva is piloting Near Miss with the New York City Department of Transportation (NYC DOT), with sensors already installed in Manhattan, Brooklyn and Queens. NYC DOT is assessing how it could use this data to prioritize safety improvement projects across the city, while simultaneously helping NYC better understand how people are using the city’s streets.
Mark Nicholson, CEO and Co-Founder at Viva, commented: “Since 2016, we have been developing Computer Vision technology to equip transport authorities with accurate, compliant road use data on all types of users. With Near Miss, we can now identify incidents hotspots before accidents happen, and help save lives.”
COO, Peter Mildon at Viva, added: “Near Miss will also help authorities to quantify the benefits of their road safety investment, as shown in the project currently running NYC DOT. We are collecting a combination of generalized Near Miss statistics so that multiple sites can be compared, and using a custom and consultative approach based on path data to understand the details behind the localized hazards.”
