Five US Departments of Transportation Upload 270,000 Miles of Road Data to Mapillary to Understand Road Safety

Road safety is a big problem in the US and a key focus for states across the country. In a big step towards ensuring road safety for their residents, Departments of Transportation in Utah, Florida, Arizona, Connecticut, and Vermont have now all made their state photologs publically available on the Mapillary platform. These images cover 270,000 miles of roads and are automatically processed with computer vision to detect guardrails, traffic signs, and pedestrians’ interactions with vehicles at scale.

A recent World Health Organization report shows that traffic injuries are the leading cause of death for people aged between 5 and 29 years in the US, and traffic accidents are estimated to cost a staggering $871 billion annually. With the US Federal Highway Administration recognizing Mapillary as an important tool in their Roadway Safety Data Program, we are announcing that five state DOTs have all uploaded complete photologs of their road networks, totaling 40 million images.

All imagery uploaded to Mapillary is automatically processed with computer vision to detect everything from traffic signs and guardrails to crosswalks and intersections. Since these DOTs have chosen to publish their photologs on Mapillary, this imagery is now publically available for all. This also means existing imagery can be used by state workers when assessing road assets like traffic signs and guardrails, instead of needing to make repetitive site visits—saving both time and taxpayers’ money while helping to ensure road safety.

Computer vision identifies guardrails and traffic signs All images on Mapillary are automatically processed with computer vision to identify objects such as these guardrails and traffic signs in Vermont

In Vermont, VTrans investigators look to the imagery side by side with GIS before heading out into the field—complementing and enhancing their existing processes. VTrans has built web-based modules using Mapillary’s Web AppBuilder Widget, addressing the specific needs of workers across traffic operations, maintenance, and project design. Roadway imagery is used for asset identification such as signs and guardrails, and viewed alongside GIS to give a better sense of roadway conditions - i.e. surface cracking in a certain area.

Monitoring road conditions is important to keep up with costly repairs and preventing further damage to roadways. In the US alone, one in five roads is considered to be in poor condition and state governments are spending billions of dollars each year on highway-related projects.

Mapåillary imager in the VTrans Roadway Imagery Viewer Mapillary imagery has been integrated into the VTrans Roadway Imagery Viewer

In Connecticut, Mapillary was identified as a solution for the Roadway Inventory Unit of CTDOT when they were tasked with integrating location-based imagery with their field data collection. Soon after, workers in other units saw how easy and non-invasive Mapillary was to use and also started collecting their own imagery when working out in the field—allowing CTDOT to greatly expand their area of coverage. Some have even enjoyed the process so much, they have started collecting imagery in their spare time.

Connecticut has rapidly grown their coverage Many workers in Connecticut have developed an interest in collecting Mapillary imagery in their spare time, allowing the state to rapidly expand coverage

Besides offering a rapid way to expand coverage of roadways, Mapillary also provides additional benefits to DOTs looking for ways to improve their road safety initiatives. The platform is a cost-effective storage solution (free with public sharing), teams can customize their imagery integrations, and GIS workers gain access to automatically extracted map data at scale.

We look forward to working with more state DOTs moving forward, for better road safety for everyone.

/Janine, VP Business Development

If you want to learn more about imagery hosting and/or updating your map data, please contact us today.

Continue the conversation
comments powered by Disqus