Nexar uses artificial intelligence for improved localization in cities
Nexar announced that it has developed a scalable method that "greatly improves GPS location accuracy in urban areas." As a benchmark to evaluate this new visual localization approach, Nexar is also releasing a dataset and benchmark based on anonymized dash cam and GPS information from its connected vehicle network to advance the research of visual localization for safety applications.
Nexar pairs dash cameras with its app, enabling vehicular alerts to what is happening on the road ahead with the help of other vehicles around it. Information on collisions, traffic, closed lanes, and dangerous road conditions ahead is shared.
To deliver these critical alerts, Nexar needs an efficient and accurate way of knowing in real time exactly where vehicles are on the road. In dense urban environments, GPS is highly inaccurate, as satellite signals are often blocked or reflected by high-rise buildings (urban canyons). Nexar's new artificial intelligence (AI)-powered image retrieval algorithm is designed to dramatically improve localization in cities. Nexar's research of crowd-sourced data of over 250,000 driving hours in New York City found that at least 40% of rides suffered GPS errors of 10 m (33 ft) or more due to the urban canyon effect.
Nexar says it has developed a hybrid coarse-to-fine approach that leverages visual and GPS location cues. According to the company, it has trained a deep-learning model to identify a driver's accurate location using its massive archive of anonymized images. The archive includes billions of these images from more than 400 million miles driven on the Nexar network.
Nexar says it has conducted experiments that confirm this localization approach is effective in challenging urban environments.
"This new localization method makes it possible for Nexar to deliver on our founding promise, which is to help rid the world of collisions," said Nexar Co-founder and Chief Technology Officer, Bruno Fernandez-Ruiz. "And the benefits will go far beyond our network—this approach could one day allow autonomous vehicles to reliably navigate cities. It's just as accurate and far less expensive than structure-based techniques such as LiDAR, which are limited in scale and expensive to compute. So the potential is really tremendous."
A research paper detailing Nexar's localization approach and findings can be found at https://arxiv.org/pdf/1905.03706v1.pdf.