Using AI to mine Google Street View
Synthetic Intelligence can now scan countless pictures taken by Google Street View to glean insights like income or ballot patterns, The New york city Times reports. In a Stanford project, computer systems scanned countless images of parked vehicles to predict ballot patterns and contamination.
Why it matters: The task at Stanford (where a computer system performed in 2 weeks what would have taken a human 15 years) reveals that computer system vision is getting clever enough, with some human training, to start mining massive visual sets of information produced by items like Google Street View.
Here’s exactly what the Stanford job had the ability to learn and predict utilizing vehicle photos, inning accordance with the Times:
- Accurately predicted “earnings, race, education and ballot patterns at the POSTAL CODE and precinct level in cities throughout the nation.”
- Using vehicle information, it discovered that Burlington, Vermont, is the nation’s greenest city and Casper, Wyoming, has the biggest carbon footprint per-capita.
- Chicago has the greatest level of income segregation and Jacksonville has the least.
- New York City has the most expensive automobiles, El Paso has the highest portion of Hummers and San Francisco has the highest percentage of foreign cars.