Amazon's Rekognition and Swedish startup Mapillary have teamed up to utilize both of their technologies to help residents find parking spaces easier within congested urban areas.
Mapillary's platform uses computer vision to enhance digital maps and road signs. However, while Mapillary has more than 350 million images on its platform and can detect 1,500 different classes of traffic signs, it is unable to actually read the text on the signs. Amazon's Rekognition, on the other hand, is a visual data analysis platform capable of doing just that, so by integrating Amazon's Rekognition software within the Mapillary platform, is now capable of reading parking signs with 95% accuracy.
Mapillary claim that the parking crunch is costing US citizens $73bn every year. Solutions to this problem usually comes in the form of more parking structures, but little is ever done to actually help customers and residents find their way to existing parking spaces. Mapillary say its solution will save both residents and cities time and money.
Visit Innovation Enterprise's Chief Technology Officer Summit in San Francisco on November 28–29, 2018
In a statement, Mapillary CEO and co-founder Jan Erik Solem said, "City authorities are struggling to keep track of their parking signs and data. For cities to manually track this themselves would cost millions of taxpayers' dollars, not to mention the enormous time investment.
"The collaboration between Mapillary and Amazon Rekognition means that several cities in the US are now in a position to get complete updates on their parking signs through an automated and computer vision-driven process, saving both time and money," he added